[PATCH] Use ZVC for inactive and active counts

The determination of the dirty ratio to determine writeback behavior is
currently based on the number of total pages on the system.

However, not all pages in the system may be dirtied.  Thus the ratio is always
too low and can never reach 100%.  The ratio may be particularly skewed if
large hugepage allocations, slab allocations or device driver buffers make
large sections of memory not available anymore.  In that case we may get into
a situation in which f.e.  the background writeback ratio of 40% cannot be
reached anymore which leads to undesired writeback behavior.

This patchset fixes that issue by determining the ratio based on the actual
pages that may potentially be dirty.  These are the pages on the active and
the inactive list plus free pages.

The problem with those counts has so far been that it is expensive to
calculate these because counts from multiple nodes and multiple zones will
have to be summed up.  This patchset makes these counters ZVC counters.  This
means that a current sum per zone, per node and for the whole system is always
available via global variables and not expensive anymore to calculate.

The patchset results in some other good side effects:

- Removal of the various functions that sum up free, active and inactive
  page counts

- Cleanup of the functions that display information via the proc filesystem.

This patch:

The use of a ZVC for nr_inactive and nr_active allows a simplification of some
counter operations.  More ZVC functionality is used for sums etc in the
following patches.

[akpm@osdl.org: UP build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 60 insertions, 51 deletions

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 3b6723dfaff..895bc4e9303 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -1,30 +1,29 @@
-
 static inline void
 add_page_to_active_list(struct zone *zone, struct page *page)
 {
 	list_add(&page->lru, &zone->active_list);
-	zone->nr_active++;
+	__inc_zone_state(zone, NR_ACTIVE);
 }
 
 static inline void
 add_page_to_inactive_list(struct zone *zone, struct page *page)
 {
 	list_add(&page->lru, &zone->inactive_list);
-	zone->nr_inactive++;
+	__inc_zone_state(zone, NR_INACTIVE);
 }
 
 static inline void
 del_page_from_active_list(struct zone *zone, struct page *page)
 {
 	list_del(&page->lru);
-	zone->nr_active--;
+	__dec_zone_state(zone, NR_ACTIVE);
 }
 
 static inline void
 del_page_from_inactive_list(struct zone *zone, struct page *page)
 {
 	list_del(&page->lru);
-	zone->nr_inactive--;
+	__dec_zone_state(zone, NR_INACTIVE);
 }
 
 static inline void
@@ -33,9 +32,9 @@ del_page_from_lru(struct zone *zone, struct page *page)
 	list_del(&page->lru);
 	if (PageActive(page)) {
 		__ClearPageActive(page);
-		zone->nr_active--;
+		__dec_zone_state(zone, NR_ACTIVE);
 	} else {
-		zone->nr_inactive--;
+		__dec_zone_state(zone, NR_INACTIVE);
 	}
 }
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b262f47961f..9137d1b9735 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -47,6 +47,8 @@ struct zone_padding {
 #endif
 
 enum zone_stat_item {
+	NR_INACTIVE,
+	NR_ACTIVE,
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
@@ -197,8 +199,6 @@ struct zone {
 	struct list_head	inactive_list;
 	unsigned long		nr_scan_active;
 	unsigned long		nr_scan_inactive;
-	unsigned long		nr_active;
-	unsigned long		nr_inactive;
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	int			all_unreclaimable; /* All pages pinned */
 
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 5e9803ed17f..c8d55bcc09b 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -186,6 +186,9 @@ void inc_zone_page_state(struct page *, enum zone_stat_item);
 void dec_zone_page_state(struct page *, enum zone_stat_item);
 
 extern void inc_zone_state(struct zone *, enum zone_stat_item);
+extern void __inc_zone_state(struct zone *, enum zone_stat_item);
+extern void dec_zone_state(struct zone *, enum zone_stat_item);
+extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
 void refresh_cpu_vm_stats(int);
 void refresh_vm_stats(void);
@@ -214,6 +217,12 @@ static inline void __inc_zone_page_state(struct page *page,
 	__inc_zone_state(page_zone(page), item);
 }
 
+static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
+{
+	atomic_long_dec(&zone->vm_stat[item]);
+	atomic_long_dec(&vm_stat[item]);
+}
+
 static inline void __dec_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f26fdc94393..07c954e5327 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1616,8 +1616,8 @@ void show_free_areas(void)
 			K(zone->pages_min),
 			K(zone->pages_low),
 			K(zone->pages_high),
-			K(zone->nr_active),
-			K(zone->nr_inactive),
+			K(zone_page_state(zone, NR_ACTIVE)),
+			K(zone_page_state(zone, NR_INACTIVE)),
 			K(zone->present_pages),
 			zone->pages_scanned,
 			(zone->all_unreclaimable ? "yes" : "no")
@@ -2684,8 +2684,6 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		INIT_LIST_HEAD(&zone->inactive_list);
 		zone->nr_scan_active = 0;
 		zone->nr_scan_inactive = 0;
-		zone->nr_active = 0;
-		zone->nr_inactive = 0;
 		zap_zone_vm_stats(zone);
 		atomic_set(&zone->reclaim_in_progress, 0);
 		if (!size)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7430df68cb6..0655d5fe73e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -679,7 +679,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		nr_taken = isolate_lru_pages(sc->swap_cluster_max,
 					     &zone->inactive_list,
 					     &page_list, &nr_scan);
-		zone->nr_inactive -= nr_taken;
+		__mod_zone_page_state(zone, NR_INACTIVE, -nr_taken);
 		zone->pages_scanned += nr_scan;
 		spin_unlock_irq(&zone->lru_lock);
 
@@ -740,7 +740,8 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
 
 static inline int zone_is_near_oom(struct zone *zone)
 {
-	return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
+	return zone->pages_scanned >= (zone_page_state(zone, NR_ACTIVE)
+				+ zone_page_state(zone, NR_INACTIVE))*3;
 }
 
 /*
@@ -825,7 +826,7 @@ force_reclaim_mapped:
 	pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
 				    &l_hold, &pgscanned);
 	zone->pages_scanned += pgscanned;
-	zone->nr_active -= pgmoved;
+	__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
 
 	while (!list_empty(&l_hold)) {
@@ -857,7 +858,7 @@ force_reclaim_mapped:
 		list_move(&page->lru, &zone->inactive_list);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
-			zone->nr_inactive += pgmoved;
+			__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
 			spin_unlock_irq(&zone->lru_lock);
 			pgdeactivate += pgmoved;
 			pgmoved = 0;
@@ -867,7 +868,7 @@ force_reclaim_mapped:
 			spin_lock_irq(&zone->lru_lock);
 		}
 	}
-	zone->nr_inactive += pgmoved;
+	__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
 	pgdeactivate += pgmoved;
 	if (buffer_heads_over_limit) {
 		spin_unlock_irq(&zone->lru_lock);
@@ -885,14 +886,14 @@ force_reclaim_mapped:
 		list_move(&page->lru, &zone->active_list);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
-			zone->nr_active += pgmoved;
+			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
 			pgmoved = 0;
 			spin_unlock_irq(&zone->lru_lock);
 			__pagevec_release(&pvec);
 			spin_lock_irq(&zone->lru_lock);
 		}
 	}
-	zone->nr_active += pgmoved;
+	__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
 
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	__count_vm_events(PGDEACTIVATE, pgdeactivate);
@@ -918,14 +919,16 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 	 * 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->nr_active >> priority) + 1;
+	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;
 
-	zone->nr_scan_inactive += (zone->nr_inactive >> priority) + 1;
+	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;
@@ -1037,7 +1040,8 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 			continue;
 
-		lru_pages += zone->nr_active + zone->nr_inactive;
+		lru_pages += zone_page_state(zone, NR_ACTIVE)
+				+ zone_page_state(zone, NR_INACTIVE);
 	}
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
@@ -1182,7 +1186,8 @@ loop_again:
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
-			lru_pages += zone->nr_active + zone->nr_inactive;
+			lru_pages += zone_page_state(zone, NR_ACTIVE)
+					+ zone_page_state(zone, NR_INACTIVE);
 		}
 
 		/*
@@ -1219,8 +1224,9 @@ loop_again:
 			if (zone->all_unreclaimable)
 				continue;
 			if (nr_slab == 0 && zone->pages_scanned >=
-				    (zone->nr_active + zone->nr_inactive) * 6)
-				zone->all_unreclaimable = 1;
+				(zone_page_state(zone, NR_ACTIVE)
+				+ zone_page_state(zone, NR_INACTIVE)) * 6)
+					zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and
 			 * the reclaim ratio is low, start doing writepage
@@ -1385,18 +1391,22 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 
 		/* For pass = 0 we don't shrink the active list */
 		if (pass > 0) {
-			zone->nr_scan_active += (zone->nr_active >> prio) + 1;
+			zone->nr_scan_active +=
+				(zone_page_state(zone, NR_ACTIVE) >> prio) + 1;
 			if (zone->nr_scan_active >= nr_pages || pass > 3) {
 				zone->nr_scan_active = 0;
-				nr_to_scan = min(nr_pages, zone->nr_active);
+				nr_to_scan = min(nr_pages,
+					zone_page_state(zone, NR_ACTIVE));
 				shrink_active_list(nr_to_scan, zone, sc, prio);
 			}
 		}
 
-		zone->nr_scan_inactive += (zone->nr_inactive >> prio) + 1;
+		zone->nr_scan_inactive +=
+			(zone_page_state(zone, NR_INACTIVE) >> prio) + 1;
 		if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
 			zone->nr_scan_inactive = 0;
-			nr_to_scan = min(nr_pages, zone->nr_inactive);
+			nr_to_scan = min(nr_pages,
+				zone_page_state(zone, NR_INACTIVE));
 			ret += shrink_inactive_list(nr_to_scan, zone, sc);
 			if (ret >= nr_pages)
 				return ret;
@@ -1408,12 +1418,7 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 
 static unsigned long count_lru_pages(void)
 {
-	struct zone *zone;
-	unsigned long ret = 0;
-
-	for_each_zone(zone)
-		ret += zone->nr_active + zone->nr_inactive;
-	return ret;
+	return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
 }
 
 /*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index bf62a823210..5462106725d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -19,12 +19,10 @@ void __get_zone_counts(unsigned long *active, unsigned long *inactive,
 	struct zone *zones = pgdat->node_zones;
 	int i;
 
-	*active = 0;
-	*inactive = 0;
+	*active = node_page_state(pgdat->node_id, NR_ACTIVE);
+	*inactive = node_page_state(pgdat->node_id, NR_INACTIVE);
 	*free = 0;
 	for (i = 0; i < MAX_NR_ZONES; i++) {
-		*active += zones[i].nr_active;
-		*inactive += zones[i].nr_inactive;
 		*free += zones[i].free_pages;
 	}
 }
@@ -34,14 +32,12 @@ void get_zone_counts(unsigned long *active,
 {
 	struct pglist_data *pgdat;
 
-	*active = 0;
-	*inactive = 0;
+	*active = global_page_state(NR_ACTIVE);
+	*inactive = global_page_state(NR_INACTIVE);
 	*free = 0;
 	for_each_online_pgdat(pgdat) {
 		unsigned long l, m, n;
 		__get_zone_counts(&l, &m, &n, pgdat);
-		*active += l;
-		*inactive += m;
 		*free += n;
 	}
 }
@@ -239,7 +235,7 @@ EXPORT_SYMBOL(mod_zone_page_state);
  * in between and therefore the atomicity vs. interrupt cannot be exploited
  * in a useful way here.
  */
-static void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
+void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
 	s8 *p = pcp->vm_stat_diff + item;
@@ -260,9 +256,8 @@ void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
 }
 EXPORT_SYMBOL(__inc_zone_page_state);
 
-void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
+void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-	struct zone *zone = page_zone(page);
 	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
 	s8 *p = pcp->vm_stat_diff + item;
 
@@ -275,6 +270,11 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 		*p = overstep;
 	}
 }
+
+void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+	__dec_zone_state(page_zone(page), item);
+}
 EXPORT_SYMBOL(__dec_zone_page_state);
 
 void inc_zone_state(struct zone *zone, enum zone_stat_item item)
@@ -454,6 +454,8 @@ const struct seq_operations fragmentation_op = {
 
 static const char * const vmstat_text[] = {
 	/* Zoned VM counters */
+	"nr_active",
+	"nr_inactive",
 	"nr_anon_pages",
 	"nr_mapped",
 	"nr_file_pages",
@@ -529,8 +531,6 @@ static int zoneinfo_show(struct seq_file *m, void *arg)
 			   "\n        min      %lu"
 			   "\n        low      %lu"
 			   "\n        high     %lu"
-			   "\n        active   %lu"
-			   "\n        inactive %lu"
 			   "\n        scanned  %lu (a: %lu i: %lu)"
 			   "\n        spanned  %lu"
 			   "\n        present  %lu",
@@ -538,8 +538,6 @@ static int zoneinfo_show(struct seq_file *m, void *arg)
 			   zone->pages_min,
 			   zone->pages_low,
 			   zone->pages_high,
-			   zone->nr_active,
-			   zone->nr_inactive,
 			   zone->pages_scanned,
 			   zone->nr_scan_active, zone->nr_scan_inactive,
 			   zone->spanned_pages,