[PATCH] Add nobh_writepage() support

Add nobh_wripage() support for the filesystems which uses
nobh_prepare_write/nobh_commit_write().

Idea here is to reduce unnecessary bufferhead creation/attachment to the
page through pageout()->block_write_full_page().  nobh_wripage() tries to
operate by directly creating bios, but it falls back to
__block_write_full_page() if it can't make progress.

Note that this is not really generic routine and can't be used for
filesystems which uses page->Private for anything other than buffer heads.
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/buffer.c

@@ -39,6 +39,7 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
+#include <linux/mpage.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 static void invalidate_bh_lrus(void);
@@ -2508,6 +2509,61 @@ int nobh_commit_write(struct file *file, struct page *page,
 }
 EXPORT_SYMBOL(nobh_commit_write);
 
+/*
+ * nobh_writepage() - based on block_full_write_page() except
+ * that it tries to operate without attaching bufferheads to
+ * the page.
+ */
+int nobh_writepage(struct page *page, get_block_t *get_block,
+			struct writeback_control *wbc)
+{
+	struct inode * const inode = page->mapping->host;
+	loff_t i_size = i_size_read(inode);
+	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset;
+	void *kaddr;
+	int ret;
+
+	/* Is the page fully inside i_size? */
+	if (page->index < end_index)
+		goto out;
+
+	/* Is the page fully outside i_size? (truncate in progress) */
+	offset = i_size & (PAGE_CACHE_SIZE-1);
+	if (page->index >= end_index+1 || !offset) {
+		/*
+		 * The page may have dirty, unmapped buffers.  For example,
+		 * they may have been added in ext3_writepage().  Make them
+		 * freeable here, so the page does not leak.
+		 */
+#if 0
+		/* Not really sure about this  - do we need this ? */
+		if (page->mapping->a_ops->invalidatepage)
+			page->mapping->a_ops->invalidatepage(page, offset);
+#endif
+		unlock_page(page);
+		return 0; /* don't care */
+	}
+
+	/*
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the  page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	kaddr = kmap_atomic(page, KM_USER0);
+	memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr, KM_USER0);
+out:
+	ret = mpage_writepage(page, get_block, wbc);
+	if (ret == -EAGAIN)
+		ret = __block_write_full_page(inode, page, get_block, wbc);
+	return ret;
+}
+EXPORT_SYMBOL(nobh_writepage);
+
 /*
  * This function assumes that ->prepare_write() uses nobh_prepare_write().
  */

fs/ext2/inode.c

@@ -626,6 +626,12 @@ ext2_nobh_prepare_write(struct file *file, struct page *page,
 	return nobh_prepare_write(page,from,to,ext2_get_block);
 }
 
+static int ext2_nobh_writepage(struct page *page,
+			struct writeback_control *wbc)
+{
+	return nobh_writepage(page, ext2_get_block, wbc);
+}
+
 static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 {
 	return generic_block_bmap(mapping,block,ext2_get_block);
@@ -675,7 +681,7 @@ struct address_space_operations ext2_aops = {
 struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
-	.writepage		= ext2_writepage,
+	.writepage		= ext2_nobh_writepage,
 	.sync_page		= block_sync_page,
 	.prepare_write		= ext2_nobh_prepare_write,
 	.commit_write		= nobh_commit_write,

fs/jfs/inode.c

@@ -286,7 +286,7 @@ static int jfs_get_block(struct inode *ip, sector_t lblock,
 
 static int jfs_writepage(struct page *page, struct writeback_control *wbc)
 {
-	return block_write_full_page(page, jfs_get_block, wbc);
+	return nobh_writepage(page, jfs_get_block, wbc);
 }
 
 static int jfs_writepages(struct address_space *mapping,

fs/mpage.c

@@ -386,8 +386,9 @@ EXPORT_SYMBOL(mpage_readpage);
  * just allocate full-size (16-page) BIOs.
  */
 static struct bio *
-mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
-	sector_t *last_block_in_bio, int *ret, struct writeback_control *wbc)
+__mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
+	sector_t *last_block_in_bio, int *ret, struct writeback_control *wbc,
+	writepage_t writepage_fn)
 {
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = page->mapping->host;
@@ -580,7 +581,13 @@ mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
 confused:
 	if (bio)
 		bio = mpage_bio_submit(WRITE, bio);
-	*ret = page->mapping->a_ops->writepage(page, wbc);
+
+	if (writepage_fn) {
+		*ret = (*writepage_fn)(page, wbc);
+	} else {
+		*ret = -EAGAIN;
+		goto out;
+	}
 	/*
 	 * The caller has a ref on the inode, so *mapping is stable
 	 */
@@ -706,8 +713,9 @@ mpage_writepages(struct address_space *mapping,
 							&mapping->flags);
 				}
 			} else {
-				bio = mpage_writepage(bio, page, get_block,
-						&last_block_in_bio, &ret, wbc);
+				bio = __mpage_writepage(bio, page, get_block,
+						&last_block_in_bio, &ret, wbc,
+						page->mapping->a_ops->writepage);
 			}
 			if (ret || (--(wbc->nr_to_write) <= 0))
 				done = 1;
@@ -735,3 +743,19 @@ mpage_writepages(struct address_space *mapping,
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepages);
+
+int mpage_writepage(struct page *page, get_block_t get_block,
+	struct writeback_control *wbc)
+{
+	int ret = 0;
+	struct bio *bio;
+	sector_t last_block_in_bio = 0;
+
+	bio = __mpage_writepage(NULL, page, get_block,
+			&last_block_in_bio, &ret, wbc, NULL);
+	if (bio)
+		mpage_bio_submit(WRITE, bio);
+
+	return ret;
+}
+EXPORT_SYMBOL(mpage_writepage);

include/linux/buffer_head.h

@@ -203,6 +203,9 @@ int file_fsync(struct file *, struct dentry *, int);
 int nobh_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
 int nobh_commit_write(struct file *, struct page *, unsigned, unsigned);
 int nobh_truncate_page(struct address_space *, loff_t);
+int nobh_writepage(struct page *page, get_block_t *get_block,
+                        struct writeback_control *wbc);
+
 
 /*
  * inline definitions

include/linux/mpage.h

@@ -11,12 +11,15 @@
  */
 
 struct writeback_control;
+typedef int (writepage_t)(struct page *page, struct writeback_control *wbc);
 
 int mpage_readpages(struct address_space *mapping, struct list_head *pages,
 				unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
 int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
+int mpage_writepage(struct page *page, get_block_t *get_block,
+		struct writeback_control *wbc);
 
 static inline int
 generic_writepages(struct address_space *mapping, struct writeback_control *wbc)