[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, 23 insertions, 90 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 96195dcb62e1..e93cc740c22b 100644
--- a/mm/mempolicy.c
+++ b/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);