[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>
diff --git a/fs/buffer.c b/fs/buffer.c
index 3dc712f..8bcbac8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3050,6 +3050,66 @@
}
/*
+ * 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 e7d3f05..a717837 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -706,6 +706,7 @@
.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 @@
.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 8824e84..3fc4238 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1559,6 +1559,7 @@
.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 @@
.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 1206267..9892268 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1462,4 +1462,5 @@
.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 a36a8e3..bfb4f29 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1521,6 +1521,7 @@
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 84bb449..e059da9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -363,6 +363,8 @@
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 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 229b6d0..f3e17d5 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -193,13 +193,18 @@
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 f4b91d7..df2c41c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -233,6 +233,7 @@
delete_from_swap_cache(page);
}
+EXPORT_SYMBOL(remove_from_swap);
#endif
/*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7b09ac5..db8a3d3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -27,6 +27,7 @@
.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 5e98b86..5a61080 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -615,6 +615,15 @@
}
/*
+ * 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 @@
retry:
return -EAGAIN;
}
+EXPORT_SYMBOL(swap_page);
/*
* Page migration was first developed in the context of the memory hotplug
@@ -674,7 +684,7 @@
* 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 @@
return 0;
}
+EXPORT_SYMBOL(migrate_page_remove_references);
/*
* Copy the page to its new location
@@ -788,6 +799,7 @@
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 @@
remove_from_swap(newpage);
return 0;
}
+EXPORT_SYMBOL(migrate_page);
/*
* migrate_pages
@@ -914,6 +927,11 @@
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
*/