[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>

fs/buffer.c

@@ -3050,68 +3050,6 @@ asmlinkage long sys_bdflush(int func, long data)
 	return 0;
 }
 
-/*
- * Migration function for pages with buffers. This function can only be used
- * if the underlying filesystem guarantees that no other references to "page"
- * exist.
- */
-#ifdef CONFIG_MIGRATION
-int buffer_migrate_page(struct page *newpage, struct page *page)
-{
-	struct address_space *mapping = page->mapping;
-	struct buffer_head *bh, *head;
-	int rc;
-
-	if (!mapping)
-		return -EAGAIN;
-
-	if (!page_has_buffers(page))
-		return migrate_page(newpage, page);
-
-	head = page_buffers(page);
-
-	rc = migrate_page_remove_references(newpage, page, 3);
-	if (rc)
-		return rc;
-
-	bh = head;
-	do {
-		get_bh(bh);
-		lock_buffer(bh);
-		bh = bh->b_this_page;
-
-	} while (bh != head);
-
-	ClearPagePrivate(page);
-	set_page_private(newpage, page_private(page));
-	set_page_private(page, 0);
-	put_page(page);
-	get_page(newpage);
-
-	bh = head;
-	do {
-		set_bh_page(bh, newpage, bh_offset(bh));
-		bh = bh->b_this_page;
-
-	} while (bh != head);
-
-	SetPagePrivate(newpage);
-
-	migrate_page_copy(newpage, page);
-
-	bh = head;
-	do {
-		unlock_buffer(bh);
- 		put_bh(bh);
-		bh = bh->b_this_page;
-
-	} while (bh != head);
-
-	return 0;
-}
-EXPORT_SYMBOL(buffer_migrate_page);
-#endif
-
 /*
  * Buffer-head allocation
  */

fs/xfs/linux-2.6/xfs_buf.c

@@ -29,6 +29,7 @@
 #include <linux/blkdev.h>
 #include <linux/hash.h>
 #include <linux/kthread.h>
+#include <linux/migrate.h>
 #include "xfs_linux.h"
 
 STATIC kmem_zone_t *xfs_buf_zone;

include/linux/migrate.h

@@ -0,0 +1,36 @@
+#ifndef _LINUX_MIGRATE_H
+#define _LINUX_MIGRATE_H
+
+#include <linux/config.h>
+#include <linux/mm.h>
+
+#ifdef CONFIG_MIGRATION
+extern int isolate_lru_page(struct page *p, struct list_head *pagelist);
+extern int putback_lru_pages(struct list_head *l);
+extern int migrate_page(struct page *, struct page *);
+extern void migrate_page_copy(struct page *, struct page *);
+extern int migrate_page_remove_references(struct page *, struct page *, int);
+extern int migrate_pages(struct list_head *l, struct list_head *t,
+		struct list_head *moved, struct list_head *failed);
+int migrate_pages_to(struct list_head *pagelist,
+			struct vm_area_struct *vma, int dest);
+extern int fail_migrate_page(struct page *, struct page *);
+
+extern int migrate_prep(void);
+
+#else
+
+static inline int isolate_lru_page(struct page *p, struct list_head *list)
+					{ return -ENOSYS; }
+static inline int putback_lru_pages(struct list_head *l) { return 0; }
+static inline int migrate_pages(struct list_head *l, struct list_head *t,
+	struct list_head *moved, struct list_head *failed) { return -ENOSYS; }
+
+static inline int migrate_prep(void) { return -ENOSYS; }
+
+/* Possible settings for the migrate_page() method in address_operations */
+#define migrate_page NULL
+#define fail_migrate_page NULL
+
+#endif /* CONFIG_MIGRATION */
+#endif /* _LINUX_MIGRATE_H */

include/linux/swap.h

@@ -175,6 +175,21 @@ extern void swap_setup(void);
 extern unsigned long try_to_free_pages(struct zone **, gfp_t);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
+extern int remove_mapping(struct address_space *mapping, struct page *page);
+
+/* 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;
+
+extern pageout_t pageout(struct page *page, struct address_space *mapping);
 
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
@@ -188,25 +203,6 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 }
 #endif
 
-#ifdef CONFIG_MIGRATION
-extern int isolate_lru_page(struct page *p);
-extern unsigned long putback_lru_pages(struct list_head *l);
-extern int migrate_page(struct page *, struct page *);
-extern void migrate_page_copy(struct page *, struct page *);
-extern int migrate_page_remove_references(struct page *, struct page *, int);
-extern unsigned long migrate_pages(struct list_head *l, struct list_head *t,
-		struct list_head *moved, struct list_head *failed);
-extern int fail_migrate_page(struct page *, struct page *);
-#else
-static inline int isolate_lru_page(struct page *p) { return -ENOSYS; }
-static inline int putback_lru_pages(struct list_head *l) { return 0; }
-static inline int migrate_pages(struct list_head *l, struct list_head *t,
-	struct list_head *moved, struct list_head *failed) { return -ENOSYS; }
-/* Possible settings for the migrate_page() method in address_operations */
-#define migrate_page NULL
-#define fail_migrate_page NULL
-#endif
-
 #ifdef CONFIG_MMU
 /* linux/mm/shmem.c */
 extern int shmem_unuse(swp_entry_t entry, struct page *page);

mm/Kconfig

@@ -137,5 +137,11 @@ config SPLIT_PTLOCK_CPUS
 # support for page migration
 #
 config MIGRATION
+	bool "Page migration"
 	def_bool y if NUMA || SPARSEMEM || DISCONTIGMEM
 	depends on SWAP
+	help
+	  Allows the migration of the physical location of pages of processes
+	  while the virtual addresses are not changed. This is useful for
+	  example on NUMA systems to put pages nearer to the processors accessing
+	  the page.

mm/Makefile

@@ -22,3 +22,5 @@ obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
+obj-$(CONFIG_MIGRATION) += migrate.o
+

mm/mempolicy.c

@@ -86,6 +86,7 @@
 #include <linux/swap.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
+#include <linux/migrate.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -95,9 +96,6 @@
 #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
 #define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2)		/* Gather statistics */
 
-/* The number of pages to migrate per call to migrate_pages() */
-#define MIGRATE_CHUNK_SIZE 256
-
 static struct kmem_cache *policy_cache;
 static struct kmem_cache *sn_cache;
 
@@ -331,17 +329,10 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	struct vm_area_struct *first, *vma, *prev;
 
 	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-		/* Must have swap device for migration */
-		if (nr_swap_pages <= 0)
-			return ERR_PTR(-ENODEV);
 
-		/*
-		 * Clear the LRU lists so pages can be isolated.
-		 * Note that pages may be moved off the LRU after we have
-		 * drained them. Those pages will fail to migrate like other
-		 * pages that may be busy.
-		 */
-		lru_add_drain_all();
+		err = migrate_prep();
+		if (err)
+			return ERR_PTR(err);
 	}
 
 	first = find_vma(mm, start);
@@ -550,92 +541,18 @@ long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	return err;
 }
 
+#ifdef CONFIG_MIGRATION
 /*
  * page migration
  */
-
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags)
 {
 	/*
 	 * Avoid migrating a page that is shared with others.
 	 */
-	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
-		if (isolate_lru_page(page))
-			list_add_tail(&page->lru, pagelist);
-	}
-}
-
-/*
- * Migrate the list 'pagelist' of pages to a certain destination.
- *
- * Specify destination with either non-NULL vma or dest_node >= 0
- * Return the number of pages not migrated or error code
- */
-static int migrate_pages_to(struct list_head *pagelist,
-			struct vm_area_struct *vma, int dest)
-{
-	LIST_HEAD(newlist);
-	LIST_HEAD(moved);
-	LIST_HEAD(failed);
-	int err = 0;
-	unsigned long offset = 0;
-	int nr_pages;
-	struct page *page;
-	struct list_head *p;
-
-redo:
-	nr_pages = 0;
-	list_for_each(p, pagelist) {
-		if (vma) {
-			/*
-			 * The address passed to alloc_page_vma is used to
-			 * generate the proper interleave behavior. We fake
-			 * the address here by an increasing offset in order
-			 * to get the proper distribution of pages.
-			 *
-			 * No decision has been made as to which page
-			 * a certain old page is moved to so we cannot
-			 * specify the correct address.
-			 */
-			page = alloc_page_vma(GFP_HIGHUSER, vma,
-					offset + vma->vm_start);
-			offset += PAGE_SIZE;
-		}
-		else
-			page = alloc_pages_node(dest, GFP_HIGHUSER, 0);
-
-		if (!page) {
-			err = -ENOMEM;
-			goto out;
-		}
-		list_add_tail(&page->lru, &newlist);
-		nr_pages++;
-		if (nr_pages > MIGRATE_CHUNK_SIZE)
-			break;
-	}
-	err = migrate_pages(pagelist, &newlist, &moved, &failed);
-
-	putback_lru_pages(&moved);	/* Call release pages instead ?? */
-
-	if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist))
-		goto redo;
-out:
-	/* Return leftover allocated pages */
-	while (!list_empty(&newlist)) {
-		page = list_entry(newlist.next, struct page, lru);
-		list_del(&page->lru);
-		__free_page(page);
-	}
-	list_splice(&failed, pagelist);
-	if (err < 0)
-		return err;
-
-	/* Calculate number of leftover pages */
-	nr_pages = 0;
-	list_for_each(p, pagelist)
-		nr_pages++;
-	return nr_pages;
+	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1)
+		isolate_lru_page(page, pagelist);
 }
 
 /*
@@ -742,8 +659,23 @@ int do_migrate_pages(struct mm_struct *mm,
 	if (err < 0)
 		return err;
 	return busy;
+
 }
 
+#else
+
+static void migrate_page_add(struct page *page, struct list_head *pagelist,
+				unsigned long flags)
+{
+}
+
+int do_migrate_pages(struct mm_struct *mm,
+	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+{
+	return -ENOSYS;
+}
+#endif
+
 long do_mbind(unsigned long start, unsigned long len,
 		unsigned long mode, nodemask_t *nmask, unsigned long flags)
 {
@@ -808,6 +740,7 @@ long do_mbind(unsigned long start, unsigned long len,
 		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	}
+
 	if (!list_empty(&pagelist))
 		putback_lru_pages(&pagelist);