[PATCH] page migration reorg

Centralize the page migration functions in anticipation of additional
tinkering.  Creates a new file mm/migrate.c

1. Extract buffer_migrate_page() from fs/buffer.c

2. Extract central migration code from vmscan.c

3. Extract some components from mempolicy.c

4. Export pageout() and remove_from_swap() from vmscan.c

5. Make it possible to configure NUMA systems without page migration
   and non-NUMA systems with page migration.

I had to so some #ifdeffing in mempolicy.c that may need a cleanup.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 2 insertions, 489 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 548e023c193..fd572bbdc9f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -42,18 +42,6 @@
 
 #include "internal.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;
-
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -304,7 +292,7 @@ static void handle_write_error(struct address_space *mapping,
  * 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
@@ -372,7 +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 */
@@ -570,481 +558,6 @@ keep:
 	return nr_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.
- */
-unsigned long putback_lru_pages(struct list_head *l)
-{
-	struct page *page;
-	struct page *page2;
-	unsigned long 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 -EAGAIN;
-
-	/*
-	 * 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.
-	 */
-	if (try_to_unmap(page, 1) == SWAP_FAIL)
-		/* A vma has VM_LOCKED set -> Permanent failure */
-		return -EPERM;
-
-	/*
-	 * Give up if we were unable to remove all mappings.
-	 */
-	if (page_mapcount(page))
-		return -EAGAIN;
-
-	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 -EAGAIN;
-	}
-
-	/*
-	 * 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)
-{
-	int rc;
-
-	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
-
-	rc = migrate_page_remove_references(newpage, page, 2);
-
-	if (rc)
-		return rc;
-
-	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.
- */
-unsigned long migrate_pages(struct list_head *from, struct list_head *to,
-		  struct list_head *moved, struct list_head *failed)
-{
-	unsigned long retry;
-	unsigned long 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;
-}
-
-/*
- * 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 (PageLRU(page)) {
-			ret = 1;
-			get_page(page);
-			ClearPageLRU(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