1 files changed, 146 insertions, 46 deletions

diff --git a/mm/swap.c b/mm/swap.c
index c02f93611a8..5602f1a1b1e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -39,6 +39,7 @@ int page_cluster;
 
 static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
 static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
 
 /*
  * This path almost never happens for VM activity - pages are normally
@@ -178,15 +179,13 @@ void put_pages_list(struct list_head *pages)
 }
 EXPORT_SYMBOL(put_pages_list);
 
-/*
- * pagevec_move_tail() must be called with IRQ disabled.
- * Otherwise this may cause nasty races.
- */
-static void pagevec_move_tail(struct pagevec *pvec)
+static void pagevec_lru_move_fn(struct pagevec *pvec,
+				void (*move_fn)(struct page *page, void *arg),
+				void *arg)
 {
 	int i;
-	int pgmoved = 0;
 	struct zone *zone = NULL;
+	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
@@ -194,29 +193,50 @@ static void pagevec_move_tail(struct pagevec *pvec)
 
 		if (pagezone != zone) {
 			if (zone)
-				spin_unlock(&zone->lru_lock);
+				spin_unlock_irqrestore(&zone->lru_lock, flags);
 			zone = pagezone;
-			spin_lock(&zone->lru_lock);
-		}
-		if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-			int lru = page_lru_base_type(page);
-			list_move_tail(&page->lru, &zone->lru[lru].list);
-			pgmoved++;
+			spin_lock_irqsave(&zone->lru_lock, flags);
 		}
+
+		(*move_fn)(page, arg);
 	}
 	if (zone)
-		spin_unlock(&zone->lru_lock);
-	__count_vm_events(PGROTATED, pgmoved);
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
 	release_pages(pvec->pages, pvec->nr, pvec->cold);
 	pagevec_reinit(pvec);
 }
 
+static void pagevec_move_tail_fn(struct page *page, void *arg)
+{
+	int *pgmoved = arg;
+	struct zone *zone = page_zone(page);
+
+	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+		enum lru_list lru = page_lru_base_type(page);
+		list_move_tail(&page->lru, &zone->lru[lru].list);
+		mem_cgroup_rotate_reclaimable_page(page);
+		(*pgmoved)++;
+	}
+}
+
+/*
+ * pagevec_move_tail() must be called with IRQ disabled.
+ * Otherwise this may cause nasty races.
+ */
+static void pagevec_move_tail(struct pagevec *pvec)
+{
+	int pgmoved = 0;
+
+	pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved);
+	__count_vm_events(PGROTATED, pgmoved);
+}
+
 /*
  * Writeback is about to end against a page which has been marked for immediate
  * reclaim.  If it still appears to be reclaimable, move it to the tail of the
  * inactive list.
  */
-void  rotate_reclaimable_page(struct page *page)
+void rotate_reclaimable_page(struct page *page)
 {
 	if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
 	    !PageUnevictable(page) && PageLRU(page)) {
@@ -347,6 +367,74 @@ void add_page_to_unevictable_list(struct page *page)
 }
 
 /*
+ * If the page can not be invalidated, it is moved to the
+ * inactive list to speed up its reclaim.  It is moved to the
+ * head of the list, rather than the tail, to give the flusher
+ * threads some time to write it out, as this is much more
+ * effective than the single-page writeout from reclaim.
+ *
+ * If the page isn't page_mapped and dirty/writeback, the page
+ * could reclaim asap using PG_reclaim.
+ *
+ * 1. active, mapped page -> none
+ * 2. active, dirty/writeback page -> inactive, head, PG_reclaim
+ * 3. inactive, mapped page -> none
+ * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
+ * 5. inactive, clean -> inactive, tail
+ * 6. Others -> none
+ *
+ * In 4, why it moves inactive's head, the VM expects the page would
+ * be write it out by flusher threads as this is much more effective
+ * than the single-page writeout from reclaim.
+ */
+static void lru_deactivate_fn(struct page *page, void *arg)
+{
+	int lru, file;
+	bool active;
+	struct zone *zone = page_zone(page);
+
+	if (!PageLRU(page))
+		return;
+
+	if (PageUnevictable(page))
+		return;
+
+	/* Some processes are using the page */
+	if (page_mapped(page))
+		return;
+
+	active = PageActive(page);
+
+	file = page_is_file_cache(page);
+	lru = page_lru_base_type(page);
+	del_page_from_lru_list(zone, page, lru + active);
+	ClearPageActive(page);
+	ClearPageReferenced(page);
+	add_page_to_lru_list(zone, page, lru);
+
+	if (PageWriteback(page) || PageDirty(page)) {
+		/*
+		 * PG_reclaim could be raced with end_page_writeback
+		 * It can make readahead confusing.  But race window
+		 * is _really_ small and  it's non-critical problem.
+		 */
+		SetPageReclaim(page);
+	} else {
+		/*
+		 * The page's writeback ends up during pagevec
+		 * We moves tha page into tail of inactive.
+		 */
+		list_move_tail(&page->lru, &zone->lru[lru].list);
+		mem_cgroup_rotate_reclaimable_page(page);
+		__count_vm_event(PGROTATED);
+	}
+
+	if (active)
+		__count_vm_event(PGDEACTIVATE);
+	update_page_reclaim_stat(zone, page, file, 0);
+}
+
+/*
  * Drain pages out of the cpu's pagevecs.
  * Either "cpu" is the current CPU, and preemption has already been
  * disabled; or "cpu" is being hot-unplugged, and is already dead.
@@ -372,6 +460,29 @@ static void drain_cpu_pagevecs(int cpu)
 		pagevec_move_tail(pvec);
 		local_irq_restore(flags);
 	}
+
+	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+	if (pagevec_count(pvec))
+		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+}
+
+/**
+ * deactivate_page - forcefully deactivate a page
+ * @page: page to deactivate
+ *
+ * This function hints the VM that @page is a good reclaim candidate,
+ * for example if its invalidation fails due to the page being dirty
+ * or under writeback.
+ */
+void deactivate_page(struct page *page)
+{
+	if (likely(get_page_unless_zero(page))) {
+		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+
+		if (!pagevec_add(pvec, page))
+			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+		put_cpu_var(lru_deactivate_pvecs);
+	}
 }
 
 void lru_add_drain(void)
@@ -516,44 +627,33 @@ void lru_add_page_tail(struct zone* zone,
 	}
 }
 
+static void ____pagevec_lru_add_fn(struct page *page, void *arg)
+{
+	enum lru_list lru = (enum lru_list)arg;
+	struct zone *zone = page_zone(page);
+	int file = is_file_lru(lru);
+	int active = is_active_lru(lru);
+
+	VM_BUG_ON(PageActive(page));
+	VM_BUG_ON(PageUnevictable(page));
+	VM_BUG_ON(PageLRU(page));
+
+	SetPageLRU(page);
+	if (active)
+		SetPageActive(page);
+	update_page_reclaim_stat(zone, page, file, active);
+	add_page_to_lru_list(zone, page, lru);
+}
+
 /*
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.
  */
 void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 {
-	int i;
-	struct zone *zone = NULL;
-
 	VM_BUG_ON(is_unevictable_lru(lru));
 
-	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		struct zone *pagezone = page_zone(page);
-		int file;
-		int active;
-
-		if (pagezone != zone) {
-			if (zone)
-				spin_unlock_irq(&zone->lru_lock);
-			zone = pagezone;
-			spin_lock_irq(&zone->lru_lock);
-		}
-		VM_BUG_ON(PageActive(page));
-		VM_BUG_ON(PageUnevictable(page));
-		VM_BUG_ON(PageLRU(page));
-		SetPageLRU(page);
-		active = is_active_lru(lru);
-		file = is_file_lru(lru);
-		if (active)
-			SetPageActive(page);
-		update_page_reclaim_stat(zone, page, file, active);
-		add_page_to_lru_list(zone, page, lru);
-	}
-	if (zone)
-		spin_unlock_irq(&zone->lru_lock);
-	release_pages(pvec->pages, pvec->nr, pvec->cold);
-	pagevec_reinit(pvec);
+	pagevec_lru_move_fn(pvec, ____pagevec_lru_add_fn, (void *)lru);
 }
 
 EXPORT_SYMBOL(____pagevec_lru_add);