[PATCH] Direct Migration V9: migrate_pages() extension

Add direct migration support with fall back to swap.

Direct migration support on top of the swap based page migration facility.

This allows the direct migration of anonymous pages and the migration of file
backed pages by dropping the associated buffers (requires writeout).

Fall back to swap out if necessary.

The patch is based on lots of patches from the hotplug project but the code
was restructured, documented and simplified as much as possible.

Note that an additional patch that defines the migrate_page() method for
filesystems is necessary in order to avoid writeback for anonymous and file
backed pages.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Mike Kravetz <kravetz@us.ibm.com>
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 227 insertions, 20 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index d85a99d28c03..13fad5fcdf79 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -52,6 +52,7 @@
 #include <linux/init.h>
 #include <linux/rmap.h>
 #include <linux/rcupdate.h>
+#include <linux/module.h>
 
 #include <asm/tlbflush.h>
 
@@ -541,7 +542,8 @@ void page_remove_rmap(struct page *page)
  * Subfunctions of try_to_unmap: try_to_unmap_one called
  * repeatedly from either try_to_unmap_anon or try_to_unmap_file.
  */
-static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
+static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
+				int ignore_refs)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -564,7 +566,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
 	 * skipped over this mm) then we should reactivate it.
 	 */
 	if ((vma->vm_flags & VM_LOCKED) ||
-			ptep_clear_flush_young(vma, address, pte)) {
+			(ptep_clear_flush_young(vma, address, pte)
+				&& !ignore_refs)) {
 		ret = SWAP_FAIL;
 		goto out_unmap;
 	}
@@ -698,7 +701,7 @@ static void try_to_unmap_cluster(unsigned long cursor,
 	pte_unmap_unlock(pte - 1, ptl);
 }
 
-static int try_to_unmap_anon(struct page *page)
+static int try_to_unmap_anon(struct page *page, int ignore_refs)
 {
 	struct anon_vma *anon_vma;
 	struct vm_area_struct *vma;
@@ -709,7 +712,7 @@ static int try_to_unmap_anon(struct page *page)
 		return ret;
 
 	list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-		ret = try_to_unmap_one(page, vma);
+		ret = try_to_unmap_one(page, vma, ignore_refs);
 		if (ret == SWAP_FAIL || !page_mapped(page))
 			break;
 	}
@@ -726,7 +729,7 @@ static int try_to_unmap_anon(struct page *page)
  *
  * This function is only called from try_to_unmap for object-based pages.
  */
-static int try_to_unmap_file(struct page *page)
+static int try_to_unmap_file(struct page *page, int ignore_refs)
 {
 	struct address_space *mapping = page->mapping;
 	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -740,7 +743,7 @@ static int try_to_unmap_file(struct page *page)
 
 	spin_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
-		ret = try_to_unmap_one(page, vma);
+		ret = try_to_unmap_one(page, vma, ignore_refs);
 		if (ret == SWAP_FAIL || !page_mapped(page))
 			goto out;
 	}
@@ -825,16 +828,16 @@ out:
  * SWAP_AGAIN	- we missed a mapping, try again later
  * SWAP_FAIL	- the page is unswappable
  */
-int try_to_unmap(struct page *page)
+int try_to_unmap(struct page *page, int ignore_refs)
 {
 	int ret;
 
 	BUG_ON(!PageLocked(page));
 
 	if (PageAnon(page))
-		ret = try_to_unmap_anon(page);
+		ret = try_to_unmap_anon(page, ignore_refs);
 	else
-		ret = try_to_unmap_file(page);
+		ret = try_to_unmap_file(page, ignore_refs);
 
 	if (!page_mapped(page))
 		ret = SWAP_SUCCESS;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index aa4b80dbe3ad..8f326ce2b690 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -483,7 +483,7 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 			if (!sc->may_swap)
 				goto keep_locked;
 
-			switch (try_to_unmap(page)) {
+			switch (try_to_unmap(page, 0)) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:
@@ -623,7 +623,7 @@ static int swap_page(struct page *page)
 	struct address_space *mapping = page_mapping(page);
 
 	if (page_mapped(page) && mapping)
-		if (try_to_unmap(page) != SWAP_SUCCESS)
+		if (try_to_unmap(page, 0) != SWAP_SUCCESS)
 			goto unlock_retry;
 
 	if (PageDirty(page)) {
@@ -659,6 +659,154 @@ unlock_retry:
 retry:
 	return -EAGAIN;
 }
+
+/*
+ * 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.
+ */
+static 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;
+}
+
+/*
+ * 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);
+}
+
+/*
+ * 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);
+
+	return 0;
+}
+
 /*
  * migrate_pages
  *
@@ -672,11 +820,6 @@ retry:
  * are movable anymore because t has become empty
  * or no retryable pages exist anymore.
  *
- * SIMPLIFIED VERSION: This implementation of migrate_pages
- * is only swapping out pages and never touches the second
- * list. The direct migration patchset
- * extends this function to avoid the use of swap.
- *
  * Return: Number of pages not migrated when "to" ran empty.
  */
 int migrate_pages(struct list_head *from, struct list_head *to,
@@ -697,6 +840,9 @@ redo:
 	retry = 0;
 
 	list_for_each_entry_safe(page, page2, from, lru) {
+		struct page *newpage = NULL;
+		struct address_space *mapping;
+
 		cond_resched();
 
 		rc = 0;
@@ -704,6 +850,9 @@ redo:
 			/* 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
@@ -740,12 +889,64 @@ redo:
 			}
 		}
 
+		if (!to) {
+			rc = swap_page(page);
+			goto next;
+		}
+
+		newpage = lru_to_page(to);
+		lock_page(newpage);
+
 		/*
-		 * Page is properly locked and writeback is complete.
+		 * Pages are properly locked and writeback is complete.
 		 * Try to migrate the page.
 		 */
-		rc = swap_page(page);
-		goto next;
+		mapping = page_mapping(page);
+		if (!mapping)
+			goto unlock_both;
+
+		/*
+		 * Trigger writeout if page is dirty
+		 */
+		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 */
+			}
+                }
+		/*
+		 * If we have no buffer or can release the buffer
+		 * then do a simple migration.
+		 */
+		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) {
+			unlock_page(newpage);
+			newpage = NULL;
+			rc = swap_page(page);
+			goto next;
+		}
+
+unlock_both:
+		unlock_page(newpage);
 
 unlock_page:
 		unlock_page(page);
@@ -758,7 +959,10 @@ next:
 			list_move(&page->lru, failed);
 			nr_failed++;
 		} else {
-			/* Success */
+			if (newpage) {
+				/* Successful migration. Return page to LRU */
+				move_to_lru(newpage);
+			}
 			list_move(&page->lru, moved);
 		}
 	}