2.6.4-rc2-mm1: vm-split-active-lists

diff -puN arch/i386/mm/hugetlbpage.c~rollup arch/i386/mm/hugetlbpage.c
@@ -411,8 +411,8 @@ static void update_and_free_page(struct 
 	htlbzone_pages--;
 	for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) {
 		map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
-				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
-				1 << PG_private | 1<< PG_writeback);
+				1 << PG_dirty | 1 << PG_active_mapped | 1 << PG_active_unmapped |
+				1 << PG_reserved | 1 << PG_private | 1<< PG_writeback);
 		set_page_count(map, 0);
 		map++;
 	}

diff -puN arch/ia64/mm/hugetlbpage.c~rollup arch/ia64/mm/hugetlbpage.c
@@ -431,8 +431,8 @@ void update_and_free_page(struct page *p
 	htlbzone_pages--;
 	for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) {
 		map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
-				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
-				1 << PG_private | 1<< PG_writeback);
+				1 << PG_dirty | 1 << PG_active_mapped | 1 << PG_active_unmapped |
+				1 << PG_reserved | 1 << PG_private | 1<< PG_writeback);
 		set_page_count(map, 0);
 		map++;
 	}

diff -puN arch/ppc64/mm/hugetlbpage.c~rollup arch/ppc64/mm/hugetlbpage.c
@@ -800,8 +800,8 @@ static void split_and_free_hugepage(stru
 	htlbpage_total--;
 	for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) {
 		map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
-				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
-				1 << PG_private | 1<< PG_writeback);
+				1 << PG_dirty | 1 << PG_active_mapped | 1 << PG_active_unmapped |
+				1 << PG_reserved | 1 << PG_private | 1<< PG_writeback);
 		set_page_count(map, 0);
 		map++;
 	}

diff -puN arch/sparc64/mm/hugetlbpage.c~rollup arch/sparc64/mm/hugetlbpage.c
@@ -365,8 +365,8 @@ static void update_and_free_page(struct 
 	htlbzone_pages--;
 	for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) {
 		map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
-				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
-				1 << PG_private | 1<< PG_writeback);
+				1 << PG_dirty | 1 << PG_active_mapped | 1 << PG_active_unmapped |
+				1 << PG_reserved | 1 << PG_private | 1<< PG_writeback);
 		set_page_count(map, 0);
 		map++;
 	}

diff -puN include/linux/mm_inline.h~rollup include/linux/mm_inline.h
@@ -1,9 +1,16 @@
 
 static inline void
-add_page_to_active_list(struct zone *zone, struct page *page)
+add_page_to_active_mapped_list(struct zone *zone, struct page *page)
 {
-	list_add(&page->lru, &zone->active_list);
-	zone->nr_active++;
+	list_add(&page->lru, &zone->active_mapped_list);
+	zone->nr_active_mapped++;
+}
+
+static inline void
+add_page_to_active_unmapped_list(struct zone *zone, struct page *page)
+{
+	list_add(&page->lru, &zone->active_unmapped_list);
+	zone->nr_active_unmapped++;
 }
 
 static inline void

@@ -14,10 +21,17 @@ add_page_to_inactive_list(struct zone *z
 }
 
 static inline void
-del_page_from_active_list(struct zone *zone, struct page *page)
+del_page_from_active_mapped_list(struct zone *zone, struct page *page)
+{
+	list_del(&page->lru);
+	zone->nr_active_mapped--;
+}
+
+static inline void
+del_page_from_active_unmapped_list(struct zone *zone, struct page *page)
 {
 	list_del(&page->lru);
-	zone->nr_active--;
+	zone->nr_active_unmapped--;
 }
 
 static inline void

@@ -31,9 +45,12 @@ static inline void
 del_page_from_lru(struct zone *zone, struct page *page)
 {
 	list_del(&page->lru);
-	if (PageActive(page)) {
-		ClearPageActive(page);
-		zone->nr_active--;
+	if (PageActiveMapped(page)) {
+		ClearPageActiveMapped(page);
+		zone->nr_active_mapped--;
+	} else if (PageActiveUnmapped(page)) {
+		ClearPageActiveUnmapped(page);
+		zone->nr_active_unmapped--;
 	} else {
 		zone->nr_inactive--;
 	}

diff -puN include/linux/mmzone.h~rollup include/linux/mmzone.h
@@ -74,11 +74,14 @@ struct zone {
 	ZONE_PADDING(_pad1_)
 
 	spinlock_t		lru_lock;	
-	struct list_head	active_list;
+	struct list_head	active_mapped_list;
+	struct list_head	active_unmapped_list;
 	struct list_head	inactive_list;
-	atomic_t		nr_scan_active;
+	atomic_t		nr_scan_active_mapped;
+	atomic_t		nr_scan_active_unmapped;
 	atomic_t		nr_scan_inactive;
-	unsigned long		nr_active;
+	unsigned long		nr_active_mapped;
+	unsigned long		nr_active_unmapped;
 	unsigned long		nr_inactive;
 	int			all_unreclaimable; /* All pages pinned */
 	unsigned long		pages_scanned;	   /* since last reclaim */

@@ -86,25 +89,6 @@ struct zone {
 	ZONE_PADDING(_pad2_)
 
 	/*
-	 * prev_priority holds the scanning priority for this zone.  It is
-	 * defined as the scanning priority at which we achieved our reclaim
-	 * target at the previous try_to_free_pages() or balance_pgdat()
-	 * invokation.
-	 *
-	 * We use prev_priority as a measure of how much stress page reclaim is
-	 * under - it drives the swappiness decision: whether to unmap mapped
-	 * pages.
-	 *
-	 * temp_priority is used to remember the scanning priority at which
-	 * this zone was successfully refilled to free_pages == pages_high.
-	 *
-	 * Access to both these fields is quite racy even on uniprocessor.  But
-	 * it is expected to average out OK.
-	 */
-	int temp_priority;
-	int prev_priority;
-
-	/*
 	 * free areas of different sizes
 	 */
 	struct free_area	free_area[MAX_ORDER];

63 lines not on this page · raw message

diff -puN include/linux/swap.h~rollup include/linux/swap.h
@@ -175,7 +175,7 @@ extern void swap_setup(void);
 /* linux/mm/vmscan.c */
 extern int try_to_free_pages(struct zone **, unsigned int, unsigned int);
 extern int shrink_all_memory(int);
-extern int vm_swappiness;
+extern int vm_mapped_page_cost;
 
 /* linux/mm/rmap.c */
 #ifdef CONFIG_MMU

diff -puN kernel/sysctl.c~rollup kernel/sysctl.c
@@ -621,6 +621,7 @@ static ctl_table kern_table[] = {
 /* Constants for minimum and maximum testing in vm_table.
    We use these as one-element integer vectors. */
 static int zero;
+static int one = 1;
 static int one_hundred = 100;
 
 

@@ -697,13 +698,13 @@ static ctl_table vm_table[] = {
 	},
 	{
 		.ctl_name	= VM_SWAPPINESS,
-		.procname	= "swappiness",
-		.data		= &vm_swappiness,
-		.maxlen		= sizeof(vm_swappiness),
+		.procname	= "mapped_page_cost",
+		.data		= &vm_mapped_page_cost,
+		.maxlen		= sizeof(vm_mapped_page_cost),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec_minmax,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &zero,
+		.extra1		= &one,
 		.extra2		= &one_hundred,
 	},
 #ifdef CONFIG_HUGETLB_PAGE

diff -puN mm/page_alloc.c~rollup mm/page_alloc.c
@@ -81,7 +81,7 @@ static void bad_page(const char *functio
 	page->flags &= ~(1 << PG_private	|
 			1 << PG_locked	|
 			1 << PG_lru	|
-			1 << PG_active	|
+			1 << PG_active_mapped	|
 			1 << PG_dirty	|
 			1 << PG_writeback);
 	set_page_count(page, 0);

@@ -217,7 +217,8 @@ static inline void free_pages_check(cons
 			1 << PG_lru	|
 			1 << PG_private |
 			1 << PG_locked	|
-			1 << PG_active	|
+			1 << PG_active_mapped	|
+			1 << PG_active_unmapped	|
 			1 << PG_reclaim	|
 			1 << PG_slab	|
 			1 << PG_writeback )))

@@ -324,7 +325,8 @@ static void prep_new_page(struct page *p
 			1 << PG_private	|
 			1 << PG_locked	|
 			1 << PG_lru	|
-			1 << PG_active	|
+			1 << PG_active_mapped	|
+			1 << PG_active_unmapped	|
 			1 << PG_dirty	|
 			1 << PG_reclaim	|
 			1 << PG_writeback )))

@@ -818,7 +820,8 @@ unsigned int nr_used_zone_pages(void)
 	struct zone *zone;
 
 	for_each_zone(zone)
-		pages += zone->nr_active + zone->nr_inactive;
+		pages += zone->nr_active_mapped + zone->nr_active_unmapped
+			+ zone->nr_inactive;
 
 	return pages;
 }

@@ -955,7 +958,7 @@ void get_zone_counts(unsigned long *acti
 	*inactive = 0;
 	*free = 0;
 	for_each_zone(zone) {
-		*active += zone->nr_active;
+		*active += zone->nr_active_mapped + zone->nr_active_unmapped;
 		*inactive += zone->nr_inactive;
 		*free += zone->free_pages;
 	}

@@ -1068,7 +1071,7 @@ void show_free_areas(void)
 			K(zone->pages_min),
 			K(zone->pages_low),
 			K(zone->pages_high),
-			K(zone->nr_active),
+			K(zone->nr_active_mapped + zone->nr_active_unmapped),
 			K(zone->nr_inactive),
 			K(zone->present_pages)
 			);

@@ -1408,8 +1411,6 @@ static void __init free_area_init_core(s
 		zone->zone_pgdat = pgdat;
 		zone->free_pages = 0;
 
-		zone->temp_priority = zone->prev_priority = DEF_PRIORITY;
-
 		/*
 		 * The per-cpu-pages pools are set to around 1000th of the
 		 * size of the zone.  But no more than 1/4 of a meg - there's

@@ -1443,11 +1444,14 @@ static void __init free_area_init_core(s
 		}
 		printk("  %s zone: %lu pages, LIFO batch:%lu\n",
 				zone_names[j], realsize, batch);
-		INIT_LIST_HEAD(&zone->active_list);
+		INIT_LIST_HEAD(&zone->active_mapped_list);
+		INIT_LIST_HEAD(&zone->active_unmapped_list);
 		INIT_LIST_HEAD(&zone->inactive_list);
-		atomic_set(&zone->nr_scan_active, 0);
+		atomic_set(&zone->nr_scan_active_mapped, 0);
+		atomic_set(&zone->nr_scan_active_unmapped, 0);
 		atomic_set(&zone->nr_scan_inactive, 0);
-		zone->nr_active = 0;
+		zone->nr_active_mapped = 0;
+		zone->nr_active_unmapped = 0;
 		zone->nr_inactive = 0;
 		if (!size)
 			continue;

diff -puN mm/swap.c~rollup mm/swap.c
@@ -58,14 +58,18 @@ int rotate_reclaimable_page(struct page 
 		return 1;
 	if (PageDirty(page))
 		return 1;
-	if (PageActive(page))
+	if (PageActiveMapped(page))
+		return 1;
+	if (PageActiveUnmapped(page))
 		return 1;
 	if (!PageLRU(page))
 		return 1;
 
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lru_lock, flags);
-	if (PageLRU(page) && !PageActive(page)) {
+	if (PageLRU(page)
+		&& !PageActiveMapped(page) && !PageActiveUnmapped(page)) {
+
 		list_del(&page->lru);
 		list_add_tail(&page->lru, &zone->inactive_list);
 		inc_page_state(pgrotated);

@@ -84,10 +88,18 @@ void fastcall activate_page(struct page 
 	struct zone *zone = page_zone(page);
 
 	spin_lock_irq(&zone->lru_lock);
-	if (PageLRU(page) && !PageActive(page)) {
+	if (PageLRU(page)
+		&& !PageActiveMapped(page) && !PageActiveUnmapped(page)) {
+
 		del_page_from_inactive_list(zone, page);
-		SetPageActive(page);
-		add_page_to_active_list(zone, page);
+
+		if (page_mapped(page)) {
+			SetPageActiveMapped(page);
+			add_page_to_active_mapped_list(zone, page);
+		} else {
+			SetPageActiveUnmapped(page);
+			add_page_to_active_unmapped_list(zone, page);
+		}
 		inc_page_state(pgactivate);
 	}
 	spin_unlock_irq(&zone->lru_lock);

@@ -102,7 +114,8 @@ void fastcall activate_page(struct page 
  */
 void fastcall mark_page_accessed(struct page *page)
 {
-	if (!PageActive(page) && PageReferenced(page) && PageLRU(page)) {
+	if (!PageActiveMapped(page) && !PageActiveUnmapped(page)
+			&& PageReferenced(page) && PageLRU(page)) {
 		activate_page(page);
 		ClearPageReferenced(page);
 	} else if (!PageReferenced(page)) {

@@ -310,9 +323,13 @@ void __pagevec_lru_add_active(struct pag
 		}
 		if (TestSetPageLRU(page))
 			BUG();
-		if (TestSetPageActive(page))
-			BUG();
-		add_page_to_active_list(zone, page);
+		if (page_mapped(page)) {
+			SetPageActiveMapped(page);
+			add_page_to_active_mapped_list(zone, page);
+		} else {
+			SetPageActiveMapped(page);
+			add_page_to_active_unmapped_list(zone, page);
+		}
 	}
 	if (zone)
 		spin_unlock_irq(&zone->lru_lock);

372 lines not on this page · raw message

diff -puN mm/filemap.c~vm-dropbehind mm/filemap.c
@@ -662,8 +662,7 @@ page_ok:
 		/*
 		 * Mark the page accessed if we read the beginning.
 		 */
-		if (!offset)
-			mark_page_accessed(page);
+		mark_page_accessed(page);
 
 		/*
 		 * Ok, we have the page, and it's up-to-date, so

diff -puN mm/swap.c~vm-dropbehind mm/swap.c
@@ -111,13 +111,8 @@ void fastcall activate_page(struct page 
  */
 void fastcall mark_page_accessed(struct page *page)
 {
-	if (!PageActiveMapped(page) && !PageActiveUnmapped(page)
-			&& PageReferenced(page) && PageLRU(page)) {
-		activate_page(page);
-		ClearPageReferenced(page);
-	} else if (!PageReferenced(page)) {
+	if (!PageReferenced(page))
 		SetPageReferenced(page);
-	}
 }
 
 EXPORT_SYMBOL(mark_page_accessed);

diff -puN mm/rmap.c~vm-dropbehind mm/rmap.c
@@ -118,7 +118,7 @@ int fastcall page_referenced(struct page
 	int referenced = 0;
 
 	if (page_test_and_clear_young(page))
-		mark_page_accessed(page);
+		referenced++;
 
 	if (TestClearPageReferenced(page))
 		referenced++;