[PATCH] Direct Migration V9: Avoid writeback / page_migrate() method

Migrate a page with buffers without requiring writeback

This introduces a new address space operation migratepage() that may be used
by a filesystem to implement its own version of page migration.

A version is provided that migrates buffers attached to pages.  Some
filesystems (ext2, ext3, xfs) are modified to utilize this feature.

The swapper address space operation are modified so that a regular
migrate_page() will occur for anonymous pages without writeback (migrate_pages
forces every anonymous page to have a swap entry).

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

10 files changed, 100 insertions, 1 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 3dc712f29d2d..8bcbac87a28c 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3050,6 +3050,66 @@ asmlinkage long sys_bdflush(int func, long data)
 }
 
 /*
+ * 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;
+
+        if (!mapping)
+                return -EAGAIN;
+
+        if (!page_has_buffers(page))
+                return migrate_page(newpage, page);
+
+        head = page_buffers(page);
+
+        if (migrate_page_remove_references(newpage, page, 3))
+                return -EAGAIN;
+
+        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
  */
 static kmem_cache_t *bh_cachep;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index e7d3f0522d01..a717837f272e 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -706,6 +706,7 @@ struct address_space_operations ext2_aops = {
         .bmap                   = ext2_bmap,
         .direct_IO              = ext2_direct_IO,
         .writepages             = ext2_writepages,
+        .migratepage            = buffer_migrate_page,
 };
 
 struct address_space_operations ext2_aops_xip = {
@@ -723,6 +724,7 @@ struct address_space_operations ext2_nobh_aops = {
         .bmap                   = ext2_bmap,
         .direct_IO              = ext2_direct_IO,
         .writepages             = ext2_writepages,
+        .migratepage            = buffer_migrate_page,
 };
 
 /*
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 8824e84f8a56..3fc4238e9703 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1559,6 +1559,7 @@ static struct address_space_operations ext3_ordered_aops = {
         .invalidatepage = ext3_invalidatepage,
         .releasepage    = ext3_releasepage,
         .direct_IO      = ext3_direct_IO,
+        .migratepage    = buffer_migrate_page,
 };
 
 static struct address_space_operations ext3_writeback_aops = {
@@ -1572,6 +1573,7 @@ static struct address_space_operations ext3_writeback_aops = {
         .invalidatepage = ext3_invalidatepage,
         .releasepage    = ext3_releasepage,
         .direct_IO      = ext3_direct_IO,
+        .migratepage    = buffer_migrate_page,
 };
 
 static struct address_space_operations ext3_journalled_aops = {
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 120626789406..9892268e3005 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1462,4 +1462,5 @@ struct address_space_operations linvfs_aops = {
         .commit_write           = generic_commit_write,
         .bmap                   = linvfs_bmap,
         .direct_IO              = linvfs_direct_IO,
+        .migratepage            = buffer_migrate_page,
 };
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index a36a8e3b703f..bfb4f2917bb6 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1521,6 +1521,7 @@ xfs_mapping_buftarg(
         struct address_space    *mapping;
         static struct address_space_operations mapping_aops = {
                 .sync_page = block_sync_page,
+                .migratepage = fail_migrate_page,
         };
 
         inode = new_inode(bdev->bd_inode->i_sb);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 84bb449b9b01..e059da947007 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -363,6 +363,8 @@ struct address_space_operations {
                         loff_t offset, unsigned long nr_segs);
         struct page* (*get_xip_page)(struct address_space *, sector_t,
                         int);
+        /* migrate the contents of a page to the specified target */
+        int (*migratepage) (struct page *, struct page *);
 };
 
 struct backing_dev_info;
@@ -1719,6 +1721,12 @@ extern void simple_release_fs(struct vfsmount **mount, int *count);
 
 extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t);
 
+#ifdef CONFIG_MIGRATION
+extern int buffer_migrate_page(struct page *, struct page *);
+#else
+#define buffer_migrate_page NULL
+#endif
+
 extern int inode_change_ok(struct inode *, struct iattr *);
 extern int __must_check inode_setattr(struct inode *, struct iattr *);
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 229b6d04b4b6..f3e17d5963c3 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -193,13 +193,18 @@ extern int isolate_lru_page(struct page *p);
 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);
+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
diff --git a/mm/rmap.c b/mm/rmap.c
index f4b91d7aa5cf..df2c41c2a9a2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -233,6 +233,7 @@ void remove_from_swap(struct page *page)
 
         delete_from_swap_cache(page);
 }
+EXPORT_SYMBOL(remove_from_swap);
 #endif
 
 /*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7b09ac503fec..db8a3d3e1636 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -27,6 +27,7 @@ static struct address_space_operations swap_aops = {
         .writepage      = swap_writepage,
         .sync_page      = block_sync_page,
         .set_page_dirty = __set_page_dirty_nobuffers,
+        .migratepage    = migrate_page,
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5e98b86feb74..5a610804cd06 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -615,6 +615,15 @@ int putback_lru_pages(struct list_head *l)
 }
 
 /*
+ * 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
  */
@@ -659,6 +668,7 @@ unlock_retry:
 retry:
         return -EAGAIN;
 }
+EXPORT_SYMBOL(swap_page);
 
 /*
  * Page migration was first developed in the context of the memory hotplug
@@ -674,7 +684,7 @@ retry:
  * 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,
+int migrate_page_remove_references(struct page *newpage,
                                 struct page *page, int nr_refs)
 {
         struct address_space *mapping = page_mapping(page);
@@ -749,6 +759,7 @@ static int migrate_page_remove_references(struct page *newpage,
 
         return 0;
 }
+EXPORT_SYMBOL(migrate_page_remove_references);
 
 /*
  * Copy the page to its new location
@@ -788,6 +799,7 @@ void migrate_page_copy(struct page *newpage, struct page *page)
         if (PageWriteback(newpage))
                 end_page_writeback(newpage);
 }
+EXPORT_SYMBOL(migrate_page_copy);
 
 /*
  * Common logic to directly migrate a single page suitable for
@@ -815,6 +827,7 @@ int migrate_page(struct page *newpage, struct page *page)
         remove_from_swap(newpage);
         return 0;
 }
+EXPORT_SYMBOL(migrate_page);
 
 /*
  * migrate_pages
@@ -914,6 +927,11 @@ redo:
                 if (!mapping)
                         goto unlock_both;
 
+                if (mapping->a_ops->migratepage) {
+                        rc = mapping->a_ops->migratepage(newpage, page);
+                        goto unlock_both;
+                }
+
                 /*
                  * Trigger writeout if page is dirty
                  */