1 files changed, 225 insertions, 662 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1838c15ca4fd..78865c849f8f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -33,39 +33,21 @@
 #include <linux/cpuset.h>
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
+#include <linux/delay.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
 
 #include <linux/swapops.h>
 
-/* possible outcome of pageout() */
-typedef enum {
-	/* failed to write page out, page is locked */
-	PAGE_KEEP,
-	/* move page to the active list, page is locked */
-	PAGE_ACTIVATE,
-	/* page has been sent to the disk successfully, page is unlocked */
-	PAGE_SUCCESS,
-	/* page is clean and locked */
-	PAGE_CLEAN,
-} pageout_t;
+#include "internal.h"
 
 struct scan_control {
-	/* Ask refill_inactive_zone, or shrink_cache to scan this many pages */
-	unsigned long nr_to_scan;
-
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
-	/* Incremented by the number of pages reclaimed */
-	unsigned long nr_reclaimed;
-
 	unsigned long nr_mapped;	/* From page_state */
 
-	/* Ask shrink_caches, or shrink_zone to scan at this priority */
-	unsigned int priority;
-
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -183,10 +165,11 @@ EXPORT_SYMBOL(remove_shrinker);
  *
  * Returns the number of slab objects which we shrunk.
  */
-int shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages)
+unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
+			unsigned long lru_pages)
 {
 	struct shrinker *shrinker;
-	int ret = 0;
+	unsigned long ret = 0;
 
 	if (scanned == 0)
 		scanned = SWAP_CLUSTER_MAX;
@@ -306,9 +289,10 @@ static void handle_write_error(struct address_space *mapping,
 }
 
 /*
- * pageout is called by shrink_list() for each dirty page. Calls ->writepage().
+ * pageout is called by shrink_page_list() for each dirty page.
+ * Calls ->writepage().
  */
-static pageout_t pageout(struct page *page, struct address_space *mapping)
+pageout_t pageout(struct page *page, struct address_space *mapping)
 {
 	/*
 	 * If the page is dirty, only perform writeback if that write
@@ -376,7 +360,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 	return PAGE_CLEAN;
 }
 
-static int remove_mapping(struct address_space *mapping, struct page *page)
+int remove_mapping(struct address_space *mapping, struct page *page)
 {
 	if (!mapping)
 		return 0;		/* truncate got there first */
@@ -414,14 +398,15 @@ cannot_free:
 }
 
 /*
- * shrink_list adds the number of reclaimed pages to sc->nr_reclaimed
+ * shrink_page_list() returns the number of reclaimed pages
  */
-static int shrink_list(struct list_head *page_list, struct scan_control *sc)
+static unsigned long shrink_page_list(struct list_head *page_list,
+					struct scan_control *sc)
 {
 	LIST_HEAD(ret_pages);
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
-	int reclaimed = 0;
+	unsigned long nr_reclaimed = 0;
 
 	cond_resched();
 
@@ -464,12 +449,9 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page)) {
-			if (!sc->may_swap)
-				goto keep_locked;
+		if (PageAnon(page) && !PageSwapCache(page))
 			if (!add_to_swap(page, GFP_ATOMIC))
 				goto activate_locked;
-		}
 #endif /* CONFIG_SWAP */
 
 		mapping = page_mapping(page);
@@ -481,12 +463,6 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 		 * processes. Try to unmap it here.
 		 */
 		if (page_mapped(page) && mapping) {
-			/*
-			 * No unmapping if we do not swap
-			 */
-			if (!sc->may_swap)
-				goto keep_locked;
-
 			switch (try_to_unmap(page, 0)) {
 			case SWAP_FAIL:
 				goto activate_locked;
@@ -561,7 +537,7 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 
 free_it:
 		unlock_page(page);
-		reclaimed++;
+		nr_reclaimed++;
 		if (!pagevec_add(&freed_pvec, page))
 			__pagevec_release_nonlru(&freed_pvec);
 		continue;
@@ -579,479 +555,10 @@ keep:
 	if (pagevec_count(&freed_pvec))
 		__pagevec_release_nonlru(&freed_pvec);
 	mod_page_state(pgactivate, pgactivate);
-	sc->nr_reclaimed += reclaimed;
-	return reclaimed;
-}
-
-#ifdef CONFIG_MIGRATION
-static inline void move_to_lru(struct page *page)
-{
-	list_del(&page->lru);
-	if (PageActive(page)) {
-		/*
-		 * lru_cache_add_active checks that
-		 * the PG_active bit is off.
-		 */
-		ClearPageActive(page);
-		lru_cache_add_active(page);
-	} else {
-		lru_cache_add(page);
-	}
-	put_page(page);
-}
-
-/*
- * Add isolated pages on the list back to the LRU.
- *
- * returns the number of pages put back.
- */
-int putback_lru_pages(struct list_head *l)
-{
-	struct page *page;
-	struct page *page2;
-	int count = 0;
-
-	list_for_each_entry_safe(page, page2, l, lru) {
-		move_to_lru(page);
-		count++;
-	}
-	return count;
-}
-
-/*
- * Non migratable page
- */
-int fail_migrate_page(struct page *newpage, struct page *page)
-{
-	return -EIO;
-}
-EXPORT_SYMBOL(fail_migrate_page);
-
-/*
- * swapout a single page
- * page is locked upon entry, unlocked on exit
- */
-static int swap_page(struct page *page)
-{
-	struct address_space *mapping = page_mapping(page);
-
-	if (page_mapped(page) && mapping)
-		if (try_to_unmap(page, 1) != SWAP_SUCCESS)
-			goto unlock_retry;
-
-	if (PageDirty(page)) {
-		/* Page is dirty, try to write it out here */
-		switch(pageout(page, mapping)) {
-		case PAGE_KEEP:
-		case PAGE_ACTIVATE:
-			goto unlock_retry;
-
-		case PAGE_SUCCESS:
-			goto retry;
-
-		case PAGE_CLEAN:
-			; /* try to free the page below */
-		}
-	}
-
-	if (PagePrivate(page)) {
-		if (!try_to_release_page(page, GFP_KERNEL) ||
-		    (!mapping && page_count(page) == 1))
-			goto unlock_retry;
-	}
-
-	if (remove_mapping(mapping, page)) {
-		/* Success */
-		unlock_page(page);
-		return 0;
-	}
-
-unlock_retry:
-	unlock_page(page);
-
-retry:
-	return -EAGAIN;
-}
-EXPORT_SYMBOL(swap_page);
-
-/*
- * Page migration was first developed in the context of the memory hotplug
- * project. The main authors of the migration code are:
- *
- * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
- * Hirokazu Takahashi <taka@valinux.co.jp>
- * Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter <clameter@sgi.com>
- */
-
-/*
- * Remove references for a page and establish the new page with the correct
- * basic settings to be able to stop accesses to the page.
- */
-int migrate_page_remove_references(struct page *newpage,
-				struct page *page, int nr_refs)
-{
-	struct address_space *mapping = page_mapping(page);
-	struct page **radix_pointer;
-
-	/*
-	 * Avoid doing any of the following work if the page count
-	 * indicates that the page is in use or truncate has removed
-	 * the page.
-	 */
-	if (!mapping || page_mapcount(page) + nr_refs != page_count(page))
-		return 1;
-
-	/*
-	 * Establish swap ptes for anonymous pages or destroy pte
-	 * maps for files.
-	 *
-	 * In order to reestablish file backed mappings the fault handlers
-	 * will take the radix tree_lock which may then be used to stop
-  	 * processses from accessing this page until the new page is ready.
-	 *
-	 * A process accessing via a swap pte (an anonymous page) will take a
-	 * page_lock on the old page which will block the process until the
-	 * migration attempt is complete. At that time the PageSwapCache bit
-	 * will be examined. If the page was migrated then the PageSwapCache
-	 * bit will be clear and the operation to retrieve the page will be
-	 * retried which will find the new page in the radix tree. Then a new
-	 * direct mapping may be generated based on the radix tree contents.
-	 *
-	 * If the page was not migrated then the PageSwapCache bit
-	 * is still set and the operation may continue.
-	 */
-	try_to_unmap(page, 1);
-
-	/*
-	 * Give up if we were unable to remove all mappings.
-	 */
-	if (page_mapcount(page))
-		return 1;
-
-	write_lock_irq(&mapping->tree_lock);
-
-	radix_pointer = (struct page **)radix_tree_lookup_slot(
-						&mapping->page_tree,
-						page_index(page));
-
-	if (!page_mapping(page) || page_count(page) != nr_refs ||
-			*radix_pointer != page) {
-		write_unlock_irq(&mapping->tree_lock);
-		return 1;
-	}
-
-	/*
-	 * Now we know that no one else is looking at the page.
-	 *
-	 * Certain minimal information about a page must be available
-	 * in order for other subsystems to properly handle the page if they
-	 * find it through the radix tree update before we are finished
-	 * copying the page.
-	 */
-	get_page(newpage);
-	newpage->index = page->index;
-	newpage->mapping = page->mapping;
-	if (PageSwapCache(page)) {
-		SetPageSwapCache(newpage);
-		set_page_private(newpage, page_private(page));
-	}
-
-	*radix_pointer = newpage;
-	__put_page(page);
-	write_unlock_irq(&mapping->tree_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(migrate_page_remove_references);
-
-/*
- * Copy the page to its new location
- */
-void migrate_page_copy(struct page *newpage, struct page *page)
-{
-	copy_highpage(newpage, page);
-
-	if (PageError(page))
-		SetPageError(newpage);
-	if (PageReferenced(page))
-		SetPageReferenced(newpage);
-	if (PageUptodate(page))
-		SetPageUptodate(newpage);
-	if (PageActive(page))
-		SetPageActive(newpage);
-	if (PageChecked(page))
-		SetPageChecked(newpage);
-	if (PageMappedToDisk(page))
-		SetPageMappedToDisk(newpage);
-
-	if (PageDirty(page)) {
-		clear_page_dirty_for_io(page);
-		set_page_dirty(newpage);
- 	}
-
-	ClearPageSwapCache(page);
-	ClearPageActive(page);
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	page->mapping = NULL;
-
-	/*
-	 * If any waiters have accumulated on the new page then
-	 * wake them up.
-	 */
-	if (PageWriteback(newpage))
-		end_page_writeback(newpage);
-}
-EXPORT_SYMBOL(migrate_page_copy);
-
-/*
- * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
- *
- * Pages are locked upon entry and exit.
- */
-int migrate_page(struct page *newpage, struct page *page)
-{
-	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
-
-	if (migrate_page_remove_references(newpage, page, 2))
-		return -EAGAIN;
-
-	migrate_page_copy(newpage, page);
-
-	/*
-	 * Remove auxiliary swap entries and replace
-	 * them with real ptes.
-	 *
-	 * Note that a real pte entry will allow processes that are not
-	 * waiting on the page lock to use the new page via the page tables
-	 * before the new page is unlocked.
-	 */
-	remove_from_swap(newpage);
-	return 0;
-}
-EXPORT_SYMBOL(migrate_page);
-
-/*
- * migrate_pages
- *
- * Two lists are passed to this function. The first list
- * contains the pages isolated from the LRU to be migrated.
- * The second list contains new pages that the pages isolated
- * can be moved to. If the second list is NULL then all
- * pages are swapped out.
- *
- * The function returns after 10 attempts or if no pages
- * are movable anymore because to has become empty
- * or no retryable pages exist anymore.
- *
- * Return: Number of pages not migrated when "to" ran empty.
- */
-int migrate_pages(struct list_head *from, struct list_head *to,
-		  struct list_head *moved, struct list_head *failed)
-{
-	int retry;
-	int nr_failed = 0;
-	int pass = 0;
-	struct page *page;
-	struct page *page2;
-	int swapwrite = current->flags & PF_SWAPWRITE;
-	int rc;
-
-	if (!swapwrite)
-		current->flags |= PF_SWAPWRITE;
-
-redo:
-	retry = 0;
-
-	list_for_each_entry_safe(page, page2, from, lru) {
-		struct page *newpage = NULL;
-		struct address_space *mapping;
-
-		cond_resched();
-
-		rc = 0;
-		if (page_count(page) == 1)
-			/* page was freed from under us. So we are done. */
-			goto next;
-
-		if (to && list_empty(to))
-			break;
-
-		/*
-		 * Skip locked pages during the first two passes to give the
-		 * functions holding the lock time to release the page. Later we
-		 * use lock_page() to have a higher chance of acquiring the
-		 * lock.
-		 */
-		rc = -EAGAIN;
-		if (pass > 2)
-			lock_page(page);
-		else
-			if (TestSetPageLocked(page))
-				goto next;
-
-		/*
-		 * Only wait on writeback if we have already done a pass where
-		 * we we may have triggered writeouts for lots of pages.
-		 */
-		if (pass > 0) {
-			wait_on_page_writeback(page);
-		} else {
-			if (PageWriteback(page))
-				goto unlock_page;
-		}
-
-		/*
-		 * Anonymous pages must have swap cache references otherwise
-		 * the information contained in the page maps cannot be
-		 * preserved.
-		 */
-		if (PageAnon(page) && !PageSwapCache(page)) {
-			if (!add_to_swap(page, GFP_KERNEL)) {
-				rc = -ENOMEM;
-				goto unlock_page;
-			}
-		}
-
-		if (!to) {
-			rc = swap_page(page);
-			goto next;
-		}
-
-		newpage = lru_to_page(to);
-		lock_page(newpage);
-
-		/*
-		 * Pages are properly locked and writeback is complete.
-		 * Try to migrate the page.
-		 */
-		mapping = page_mapping(page);
-		if (!mapping)
-			goto unlock_both;
-
-		if (mapping->a_ops->migratepage) {
-			/*
-			 * Most pages have a mapping and most filesystems
-			 * should provide a migration function. Anonymous
-			 * pages are part of swap space which also has its
-			 * own migration function. This is the most common
-			 * path for page migration.
-			 */
-			rc = mapping->a_ops->migratepage(newpage, page);
-			goto unlock_both;
-                }
-
-		/*
-		 * Default handling if a filesystem does not provide
-		 * a migration function. We can only migrate clean
-		 * pages so try to write out any dirty pages first.
-		 */
-		if (PageDirty(page)) {
-			switch (pageout(page, mapping)) {
-			case PAGE_KEEP:
-			case PAGE_ACTIVATE:
-				goto unlock_both;
-
-			case PAGE_SUCCESS:
-				unlock_page(newpage);
-				goto next;
-
-			case PAGE_CLEAN:
-				; /* try to migrate the page below */
-			}
-                }
-
-		/*
-		 * Buffers are managed in a filesystem specific way.
-		 * We must have no buffers or drop them.
-		 */
-		if (!page_has_buffers(page) ||
-		    try_to_release_page(page, GFP_KERNEL)) {
-			rc = migrate_page(newpage, page);
-			goto unlock_both;
-		}
-
-		/*
-		 * On early passes with mapped pages simply
-		 * retry. There may be a lock held for some
-		 * buffers that may go away. Later
-		 * swap them out.
-		 */
-		if (pass > 4) {
-			/*
-			 * Persistently unable to drop buffers..... As a
-			 * measure of last resort we fall back to
-			 * swap_page().
-			 */
-			unlock_page(newpage);
-			newpage = NULL;
-			rc = swap_page(page);
-			goto next;
-		}
-
-unlock_both:
-		unlock_page(newpage);
-
-unlock_page:
-		unlock_page(page);
-
-next:
-		if (rc == -EAGAIN) {
-			retry++;
-		} else if (rc) {
-			/* Permanent failure */
-			list_move(&page->lru, failed);
-			nr_failed++;
-		} else {
-			if (newpage) {
-				/* Successful migration. Return page to LRU */
-				move_to_lru(newpage);
-			}
-			list_move(&page->lru, moved);
-		}
-	}
-	if (retry && pass++ < 10)
-		goto redo;
-
-	if (!swapwrite)
-		current->flags &= ~PF_SWAPWRITE;
-
-	return nr_failed + retry;
+	return nr_reclaimed;
 }
 
 /*
- * Isolate one page from the LRU lists and put it on the
- * indicated list with elevated refcount.
- *
- * Result:
- *  0 = page not on LRU list
- *  1 = page removed from LRU list and added to the specified list.
- */
-int isolate_lru_page(struct page *page)
-{
-	int ret = 0;
-
-	if (PageLRU(page)) {
-		struct zone *zone = page_zone(page);
-		spin_lock_irq(&zone->lru_lock);
-		if (TestClearPageLRU(page)) {
-			ret = 1;
-			get_page(page);
-			if (PageActive(page))
-				del_page_from_active_list(zone, page);
-			else
-				del_page_from_inactive_list(zone, page);
-		}
-		spin_unlock_irq(&zone->lru_lock);
-	}
-
-	return ret;
-}
-#endif
-
-/*
  * zone->lru_lock is heavily contended.  Some of the functions that
  * shrink the lists perform better by taking out a batch of pages
  * and working on them outside the LRU lock.
@@ -1068,32 +575,35 @@ int isolate_lru_page(struct page *page)
  *
  * returns how many pages were moved onto *@dst.
  */
-static int isolate_lru_pages(int nr_to_scan, struct list_head *src,
-			     struct list_head *dst, int *scanned)
+static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
+		struct list_head *src, struct list_head *dst,
+		unsigned long *scanned)
 {
-	int nr_taken = 0;
+	unsigned long nr_taken = 0;
 	struct page *page;
-	int scan = 0;
+	unsigned long scan;
 
-	while (scan++ < nr_to_scan && !list_empty(src)) {
+	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+		struct list_head *target;
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
 
-		if (!TestClearPageLRU(page))
-			BUG();
+		BUG_ON(!PageLRU(page));
+
 		list_del(&page->lru);
-		if (get_page_testone(page)) {
+		target = src;
+		if (likely(get_page_unless_zero(page))) {
 			/*
-			 * It is being freed elsewhere
+			 * Be careful not to clear PageLRU until after we're
+			 * sure the page is not being freed elsewhere -- the
+			 * page release code relies on it.
 			 */
-			__put_page(page);
-			SetPageLRU(page);
-			list_add(&page->lru, src);
-			continue;
-		} else {
-			list_add(&page->lru, dst);
+			ClearPageLRU(page);
+			target = dst;
 			nr_taken++;
-		}
+		} /* else it is being freed elsewhere */
+
+		list_add(&page->lru, target);
 	}
 
 	*scanned = scan;
@@ -1101,23 +611,26 @@ static int isolate_lru_pages(int nr_to_scan, struct list_head *src,
 }
 
 /*
- * shrink_cache() adds the number of pages reclaimed to sc->nr_reclaimed
+ * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
+ * of reclaimed pages
  */
-static void shrink_cache(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_inactive_list(unsigned long max_scan,
+				struct zone *zone, struct scan_control *sc)
 {
 	LIST_HEAD(page_list);
 	struct pagevec pvec;
-	int max_scan = sc->nr_to_scan;
+	unsigned long nr_scanned = 0;
+	unsigned long nr_reclaimed = 0;
 
 	pagevec_init(&pvec, 1);
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
-	while (max_scan > 0) {
+	do {
 		struct page *page;
-		int nr_taken;
-		int nr_scan;
-		int nr_freed;
+		unsigned long nr_taken;
+		unsigned long nr_scan;
+		unsigned long nr_freed;
 
 		nr_taken = isolate_lru_pages(sc->swap_cluster_max,
 					     &zone->inactive_list,
@@ -1126,12 +639,9 @@ static void shrink_cache(struct zone *zone, struct scan_control *sc)
 		zone->pages_scanned += nr_scan;
 		spin_unlock_irq(&zone->lru_lock);
 
-		if (nr_taken == 0)
-			goto done;
-
-		max_scan -= nr_scan;
-		nr_freed = shrink_list(&page_list, sc);
-
+		nr_scanned += nr_scan;
+		nr_freed = shrink_page_list(&page_list, sc);
+		nr_reclaimed += nr_freed;
 		local_irq_disable();
 		if (current_is_kswapd()) {
 			__mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
@@ -1140,14 +650,17 @@ static void shrink_cache(struct zone *zone, struct scan_control *sc)
 			__mod_page_state_zone(zone, pgscan_direct, nr_scan);
 		__mod_page_state_zone(zone, pgsteal, nr_freed);
 
+		if (nr_taken == 0)
+			goto done;
+
 		spin_lock(&zone->lru_lock);
 		/*
 		 * Put back any unfreeable pages.
 		 */
 		while (!list_empty(&page_list)) {
 			page = lru_to_page(&page_list);
-			if (TestSetPageLRU(page))
-				BUG();
+			BUG_ON(PageLRU(page));
+			SetPageLRU(page);
 			list_del(&page->lru);
 			if (PageActive(page))
 				add_page_to_active_list(zone, page);
@@ -1159,10 +672,12 @@ static void shrink_cache(struct zone *zone, struct scan_control *sc)
 				spin_lock_irq(&zone->lru_lock);
 			}
 		}
-  	}
-	spin_unlock_irq(&zone->lru_lock);
+  	} while (nr_scanned < max_scan);
+	spin_unlock(&zone->lru_lock);
 done:
+	local_irq_enable();
 	pagevec_release(&pvec);
+	return nr_reclaimed;
 }
 
 /*
@@ -1182,13 +697,12 @@ done:
  * The downside is that we have to touch page->_count against each page.
  * But we had to alter page->flags anyway.
  */
-static void
-refill_inactive_zone(struct zone *zone, struct scan_control *sc)
+static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
+				struct scan_control *sc)
 {
-	int pgmoved;
+	unsigned long pgmoved;
 	int pgdeactivate = 0;
-	int pgscanned;
-	int nr_pages = sc->nr_to_scan;
+	unsigned long pgscanned;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
 	LIST_HEAD(l_inactive);	/* Pages to go onto the inactive_list */
 	LIST_HEAD(l_active);	/* Pages to go onto the active_list */
@@ -1196,7 +710,7 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 	struct pagevec pvec;
 	int reclaim_mapped = 0;
 
-	if (unlikely(sc->may_swap)) {
+	if (sc->may_swap) {
 		long mapped_ratio;
 		long distress;
 		long swap_tendency;
@@ -1266,10 +780,11 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
 		prefetchw_prev_lru_page(page, &l_inactive, flags);
-		if (TestSetPageLRU(page))
-			BUG();
-		if (!TestClearPageActive(page))
-			BUG();
+		BUG_ON(PageLRU(page));
+		SetPageLRU(page);
+		BUG_ON(!PageActive(page));
+		ClearPageActive(page);
+
 		list_move(&page->lru, &zone->inactive_list);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
@@ -1295,8 +810,8 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 	while (!list_empty(&l_active)) {
 		page = lru_to_page(&l_active);
 		prefetchw_prev_lru_page(page, &l_active, flags);
-		if (TestSetPageLRU(page))
-			BUG();
+		BUG_ON(PageLRU(page));
+		SetPageLRU(page);
 		BUG_ON(!PageActive(page));
 		list_move(&page->lru, &zone->active_list);
 		pgmoved++;
@@ -1321,11 +836,13 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
-static void
-shrink_zone(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_zone(int priority, struct zone *zone,
+				struct scan_control *sc)
 {
 	unsigned long nr_active;
 	unsigned long nr_inactive;
+	unsigned long nr_to_scan;
+	unsigned long nr_reclaimed = 0;
 
 	atomic_inc(&zone->reclaim_in_progress);
 
@@ -1333,14 +850,14 @@ shrink_zone(struct zone *zone, struct scan_control *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->nr_active >> sc->priority) + 1;
+	zone->nr_scan_active += (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 >> sc->priority) + 1;
+	zone->nr_scan_inactive += (zone->nr_inactive >> priority) + 1;
 	nr_inactive = zone->nr_scan_inactive;
 	if (nr_inactive >= sc->swap_cluster_max)
 		zone->nr_scan_inactive = 0;
@@ -1349,23 +866,25 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
 
 	while (nr_active || nr_inactive) {
 		if (nr_active) {
-			sc->nr_to_scan = min(nr_active,
+			nr_to_scan = min(nr_active,
 					(unsigned long)sc->swap_cluster_max);
-			nr_active -= sc->nr_to_scan;
-			refill_inactive_zone(zone, sc);
+			nr_active -= nr_to_scan;
+			shrink_active_list(nr_to_scan, zone, sc);
 		}
 
 		if (nr_inactive) {
-			sc->nr_to_scan = min(nr_inactive,
+			nr_to_scan = min(nr_inactive,
 					(unsigned long)sc->swap_cluster_max);
-			nr_inactive -= sc->nr_to_scan;
-			shrink_cache(zone, sc);
+			nr_inactive -= nr_to_scan;
+			nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
+								sc);
 		}
 	}
 
 	throttle_vm_writeout();
 
 	atomic_dec(&zone->reclaim_in_progress);
+	return nr_reclaimed;
 }
 
 /*
@@ -1384,9 +903,10 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static void
-shrink_caches(struct zone **zones, struct scan_control *sc)
+static unsigned long shrink_zones(int priority, struct zone **zones,
+					struct scan_control *sc)
 {
+	unsigned long nr_reclaimed = 0;
 	int i;
 
 	for (i = 0; zones[i] != NULL; i++) {
@@ -1398,15 +918,16 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->temp_priority = sc->priority;
-		if (zone->prev_priority > sc->priority)
-			zone->prev_priority = sc->priority;
+		zone->temp_priority = priority;
+		if (zone->prev_priority > priority)
+			zone->prev_priority = priority;
 
-		if (zone->all_unreclaimable && sc->priority != DEF_PRIORITY)
+		if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 			continue;	/* Let kswapd poll it */
 
-		shrink_zone(zone, sc);
+		nr_reclaimed += shrink_zone(priority, zone, sc);
 	}
+	return nr_reclaimed;
 }
  
 /*
@@ -1422,19 +943,21 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
  */
-int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
+unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 {
 	int priority;
 	int ret = 0;
-	int total_scanned = 0, total_reclaimed = 0;
+	unsigned long total_scanned = 0;
+	unsigned long nr_reclaimed = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct scan_control sc;
 	unsigned long lru_pages = 0;
 	int i;
-
-	sc.gfp_mask = gfp_mask;
-	sc.may_writepage = !laptop_mode;
-	sc.may_swap = 1;
+	struct scan_control sc = {
+		.gfp_mask = gfp_mask,
+		.may_writepage = !laptop_mode,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.may_swap = 1,
+	};
 
 	inc_page_state(allocstall);
 
@@ -1451,20 +974,16 @@ int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc.nr_mapped = read_page_state(nr_mapped);
 		sc.nr_scanned = 0;
-		sc.nr_reclaimed = 0;
-		sc.priority = priority;
-		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
 		if (!priority)
 			disable_swap_token();
-		shrink_caches(zones, &sc);
+		nr_reclaimed += shrink_zones(priority, zones, &sc);
 		shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
 		if (reclaim_state) {
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+			nr_reclaimed += reclaim_state->reclaimed_slab;
 			reclaim_state->reclaimed_slab = 0;
 		}
 		total_scanned += sc.nr_scanned;
-		total_reclaimed += sc.nr_reclaimed;
-		if (total_reclaimed >= sc.swap_cluster_max) {
+		if (nr_reclaimed >= sc.swap_cluster_max) {
 			ret = 1;
 			goto out;
 		}
@@ -1476,7 +995,8 @@ int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		 * that's undesirable in laptop mode, where we *want* lumpy
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
-		if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
+		if (total_scanned > sc.swap_cluster_max +
+					sc.swap_cluster_max / 2) {
 			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
 			sc.may_writepage = 1;
 		}
@@ -1522,22 +1042,26 @@ out:
  * the page allocator fallback scheme to ensure that aging of pages is balanced
  * across the zones.
  */
-static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
+				int order)
 {
-	int to_free = nr_pages;
+	unsigned long to_free = nr_pages;
 	int all_zones_ok;
 	int priority;
 	int i;
-	int total_scanned, total_reclaimed;
+	unsigned long total_scanned;
+	unsigned long nr_reclaimed;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct scan_control sc;
+	struct scan_control sc = {
+		.gfp_mask = GFP_KERNEL,
+		.may_swap = 1,
+		.swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX,
+	};
 
 loop_again:
 	total_scanned = 0;
-	total_reclaimed = 0;
-	sc.gfp_mask = GFP_KERNEL;
-	sc.may_writepage = !laptop_mode;
-	sc.may_swap = 1;
+	nr_reclaimed = 0;
+	sc.may_writepage = !laptop_mode,
 	sc.nr_mapped = read_page_state(nr_mapped);
 
 	inc_page_state(pageoutrun);
@@ -1618,15 +1142,11 @@ scan:
 			if (zone->prev_priority > priority)
 				zone->prev_priority = priority;
 			sc.nr_scanned = 0;
-			sc.nr_reclaimed = 0;
-			sc.priority = priority;
-			sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
-			shrink_zone(zone, &sc);
+			nr_reclaimed += shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
 						lru_pages);
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-			total_reclaimed += sc.nr_reclaimed;
+			nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 			if (zone->all_unreclaimable)
 				continue;
@@ -1639,10 +1159,10 @@ scan:
 			 * even in laptop mode
 			 */
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > total_reclaimed+total_reclaimed/2)
+			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
 				sc.may_writepage = 1;
 		}
-		if (nr_pages && to_free > total_reclaimed)
+		if (nr_pages && to_free > nr_reclaimed)
 			continue;	/* swsusp: need to do more work */
 		if (all_zones_ok)
 			break;		/* kswapd: all done */
@@ -1659,7 +1179,7 @@ scan:
 		 * matches the direct reclaim path behaviour in terms of impact
 		 * on zone->*_priority.
 		 */
-		if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
+		if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages)
 			break;
 	}
 out:
@@ -1673,7 +1193,7 @@ out:
 		goto loop_again;
 	}
 
-	return total_reclaimed;
+	return nr_reclaimed;
 }
 
 /*
@@ -1773,24 +1293,31 @@ void wakeup_kswapd(struct zone *zone, int order)
  * Try to free `nr_pages' of memory, system-wide.  Returns the number of freed
  * pages.
  */
-int shrink_all_memory(int nr_pages)
+unsigned long shrink_all_memory(unsigned long nr_pages)
 {
 	pg_data_t *pgdat;
-	int nr_to_free = nr_pages;
-	int ret = 0;
+	unsigned long nr_to_free = nr_pages;
+	unsigned long ret = 0;
+	unsigned retry = 2;
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
 
 	current->reclaim_state = &reclaim_state;
+repeat:
 	for_each_pgdat(pgdat) {
-		int freed;
+		unsigned long freed;
+
 		freed = balance_pgdat(pgdat, nr_to_free, 0);
 		ret += freed;
 		nr_to_free -= freed;
-		if (nr_to_free <= 0)
+		if ((long)nr_to_free <= 0)
 			break;
 	}
+	if (retry-- && ret < nr_pages) {
+		blk_congestion_wait(WRITE, HZ/5);
+		goto repeat;
+	}
 	current->reclaim_state = NULL;
 	return ret;
 }
@@ -1802,8 +1329,7 @@ int shrink_all_memory(int nr_pages)
    away, we get changed to run anywhere: as the first one comes back,
    restore their cpu bindings. */
 static int __devinit cpu_callback(struct notifier_block *nfb,
-				  unsigned long action,
-				  void *hcpu)
+				  unsigned long action, void *hcpu)
 {
 	pg_data_t *pgdat;
 	cpumask_t mask;
@@ -1823,10 +1349,17 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 static int __init kswapd_init(void)
 {
 	pg_data_t *pgdat;
+
 	swap_setup();
-	for_each_pgdat(pgdat)
-		pgdat->kswapd
-		= find_task_by_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
+	for_each_pgdat(pgdat) {
+		pid_t pid;
+
+		pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
+		BUG_ON(pid < 0);
+		read_lock(&tasklist_lock);
+		pgdat->kswapd = find_task_by_pid(pid);
+		read_unlock(&tasklist_lock);
+	}
 	total_memory = nr_free_pagecache_pages();
 	hotcpu_notifier(cpu_callback, 0);
 	return 0;
@@ -1868,47 +1401,31 @@ int zone_reclaim_interval __read_mostly = 30*HZ;
 /*
  * Try to free up some pages from this zone through reclaim.
  */
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 {
-	int nr_pages;
+	/* Minimum pages needed in order to stay on node */
+	const unsigned long nr_pages = 1 << order;
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
-	struct scan_control sc;
-	cpumask_t mask;
-	int node_id;
-
-	if (time_before(jiffies,
-		zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
-			return 0;
-
-	if (!(gfp_mask & __GFP_WAIT) ||
-		zone->all_unreclaimable ||
-		atomic_read(&zone->reclaim_in_progress) > 0)
-			return 0;
-
-	node_id = zone->zone_pgdat->node_id;
-	mask = node_to_cpumask(node_id);
-	if (!cpus_empty(mask) && node_id != numa_node_id())
-		return 0;
-
-	sc.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE);
-	sc.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP);
-	sc.nr_scanned = 0;
-	sc.nr_reclaimed = 0;
-	sc.priority = ZONE_RECLAIM_PRIORITY + 1;
-	sc.nr_mapped = read_page_state(nr_mapped);
-	sc.gfp_mask = gfp_mask;
+	int priority;
+	unsigned long nr_reclaimed = 0;
+	struct scan_control sc = {
+		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
+		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.nr_mapped = read_page_state(nr_mapped),
+		.swap_cluster_max = max_t(unsigned long, nr_pages,
+					SWAP_CLUSTER_MAX),
+		.gfp_mask = gfp_mask,
+	};
 
 	disable_swap_token();
-
-	nr_pages = 1 << order;
-	if (nr_pages > SWAP_CLUSTER_MAX)
-		sc.swap_cluster_max = nr_pages;
-	else
-		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
-
 	cond_resched();
-	p->flags |= PF_MEMALLOC;
+	/*
+	 * We need to be able to allocate from the reserves for RECLAIM_SWAP
+	 * and we also need to be able to write out pages for RECLAIM_WRITE
+	 * and RECLAIM_SWAP.
+	 */
+	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
@@ -1916,32 +1433,78 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 * Free memory by calling shrink zone with increasing priorities
 	 * until we have enough memory freed.
 	 */
+	priority = ZONE_RECLAIM_PRIORITY;
 	do {
-		sc.priority--;
-		shrink_zone(zone, &sc);
-
-	} while (sc.nr_reclaimed < nr_pages && sc.priority > 0);
+		nr_reclaimed += shrink_zone(priority, zone, &sc);
+		priority--;
+	} while (priority >= 0 && nr_reclaimed < nr_pages);
 
-	if (sc.nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+	if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
 		/*
-		 * shrink_slab does not currently allow us to determine
-		 * how many pages were freed in the zone. So we just
-		 * shake the slab and then go offnode for a single allocation.
+		 * shrink_slab() does not currently allow us to determine how
+		 * many pages were freed in this zone. So we just shake the slab
+		 * a bit and then go off node for this particular allocation
+		 * despite possibly having freed enough memory to allocate in
+		 * this zone.  If we freed local memory then the next
+		 * allocations will be local again.
 		 *
 		 * shrink_slab will free memory on all zones and may take
 		 * a long time.
 		 */
 		shrink_slab(sc.nr_scanned, gfp_mask, order);
-		sc.nr_reclaimed = 1;    /* Avoid getting the off node timeout */
 	}
 
 	p->reclaim_state = NULL;
-	current->flags &= ~PF_MEMALLOC;
+	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
 
-	if (sc.nr_reclaimed == 0)
+	if (nr_reclaimed == 0) {
+		/*
+		 * We were unable to reclaim enough pages to stay on node.  We
+		 * now allow off node accesses for a certain time period before
+		 * trying again to reclaim pages from the local zone.
+		 */
 		zone->last_unsuccessful_zone_reclaim = jiffies;
+	}
 
-	return sc.nr_reclaimed >= nr_pages;
+	return nr_reclaimed >= nr_pages;
 }
-#endif
 
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+{
+	cpumask_t mask;
+	int node_id;
+
+	/*
+	 * Do not reclaim if there was a recent unsuccessful attempt at zone
+	 * reclaim.  In that case we let allocations go off node for the
+	 * zone_reclaim_interval.  Otherwise we would scan for each off-node
+	 * page allocation.
+	 */
+	if (time_before(jiffies,
+		zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
+			return 0;
+
+	/*
+	 * Avoid concurrent zone reclaims, do not reclaim in a zone that does
+	 * not have reclaimable pages and if we should not delay the allocation
+	 * then do not scan.
+	 */
+	if (!(gfp_mask & __GFP_WAIT) ||
+		zone->all_unreclaimable ||
+		atomic_read(&zone->reclaim_in_progress) > 0 ||
+		(current->flags & PF_MEMALLOC))
+			return 0;
+
+	/*
+	 * Only run zone reclaim on the local zone or on zones that do not
+	 * have associated processors. This will favor the local processor
+	 * over remote processors and spread off node memory allocations
+	 * as wide as possible.
+	 */
+	node_id = zone->zone_pgdat->node_id;
+	mask = node_to_cpumask(node_id);
+	if (!cpus_empty(mask) && node_id != numa_node_id())
+		return 0;
+	return __zone_reclaim(zone, gfp_mask, order);
+}
+#endif