Buffered write deadlock fix and new aops for 2.6.21-rc6-mm1

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1980,27 +1980,21 @@ generic_file_buffered_write(struct kiocb
 		/* Limit the size of the copy to the caller's write size */
 		bytes = min(bytes, count);
 
-		/* We only need to worry about prefaulting when writes are from
-		 * user-space.  NFSd uses vfs_writev with several non-aligned
-		 * segments in the vector, and limiting to one segment a time is
-		 * a noticeable performance for re-write
+		/*
+		 * Limit the size of the copy to that of the current segment,
+		 * because fault_in_pages_readable() doesn't know how to walk
+		 * segments.
 		 */
-		if (!segment_eq(get_fs(), KERNEL_DS)) {
-			/*
-			 * Limit the size of the copy to that of the current
-			 * segment, because fault_in_pages_readable() doesn't
-			 * know how to walk segments.
-			 */
-			bytes = min(bytes, cur_iov->iov_len - iov_base);
+		bytes = min(bytes, cur_iov->iov_len - iov_base);
+
+		/*
+		 * Bring in the user page that we will copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 */
+		fault_in_pages_readable(buf, bytes);
 
-			/*
-			 * Bring in the user page that we will copy from
-			 * _first_.  Otherwise there's a nasty deadlock on
-			 * copying from the same page as we're writing to,
-			 * without it being marked up-to-date.
-			 */
-			fault_in_pages_readable(buf, bytes);
-		}
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {
 			status = -ENOMEM;

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -2001,12 +2001,6 @@ generic_file_buffered_write(struct kiocb
 			break;
 		}
 
-		if (unlikely(bytes == 0)) {
-			status = 0;
-			copied = 0;
-			goto zero_length_segment;
-		}
-
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
 		if (unlikely(status)) {
 			loff_t isize = i_size_read(inode);

@@ -2036,8 +2030,7 @@ generic_file_buffered_write(struct kiocb
 			page_cache_release(page);
 			continue;
 		}
-zero_length_segment:
-		if (likely(copied >= 0)) {
+		if (likely(copied > 0)) {
 			if (!status)
 				status = copied;
 

Index: linux-2.6/mm/filemap.h
===================================================================
@@ -87,7 +87,7 @@ filemap_set_next_iovec(const struct iove
 	const struct iovec *iov = *iovp;
 	size_t base = *basep;
 
-	do {
+	while (bytes) {
 		int copy = min(bytes, iov->iov_len - base);
 
 		bytes -= copy;

@@ -96,7 +96,7 @@ filemap_set_next_iovec(const struct iove
 			iov++;
 			base = 0;
 		}
-	} while (bytes);
+	}
 	*iovp = iov;
 	*basep = base;
 }

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1971,21 +1971,14 @@ generic_file_buffered_write(struct kiocb
 	do {
 		unsigned long index;
 		unsigned long offset;
+		unsigned long maxlen;
 		size_t copied;
 
 		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
-
-		/* Limit the size of the copy to the caller's write size */
-		bytes = min(bytes, count);
-
-		/*
-		 * Limit the size of the copy to that of the current segment,
-		 * because fault_in_pages_readable() doesn't know how to walk
-		 * segments.
-		 */
-		bytes = min(bytes, cur_iov->iov_len - iov_base);
+		if (bytes > count)
+			bytes = count;
 
 		/*
 		 * Bring in the user page that we will copy from _first_.

@@ -1993,7 +1986,10 @@ generic_file_buffered_write(struct kiocb
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		fault_in_pages_readable(buf, bytes);
+		maxlen = cur_iov->iov_len - iov_base;
+		if (maxlen > bytes)
+			maxlen = bytes;
+		fault_in_pages_readable(buf, maxlen);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1944,16 +1944,15 @@ generic_file_buffered_write(struct kiocb
 		size_t count, ssize_t written)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space * mapping = file->f_mapping;
+	struct address_space *mapping = file->f_mapping;
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	struct inode 	*inode = mapping->host;
 	long		status = 0;
 	struct page	*page;
 	struct page	*cached_page = NULL;
-	size_t		bytes;
 	struct pagevec	lru_pvec;
 	const struct iovec *cur_iov = iov; /* current iovec */
-	size_t		iov_base = 0;	   /* offset in the current iovec */
+	size_t		iov_offset = 0;	   /* offset in the current iovec */
 	char __user	*buf;
 
 	pagevec_init(&lru_pvec, 0);

@@ -1964,31 +1963,33 @@ generic_file_buffered_write(struct kiocb
 	if (likely(nr_segs == 1))
 		buf = iov->iov_base + written;
 	else {
-		filemap_set_next_iovec(&cur_iov, &iov_base, written);
-		buf = cur_iov->iov_base + iov_base;
+		filemap_set_next_iovec(&cur_iov, &iov_offset, written);
+		buf = cur_iov->iov_base + iov_offset;
 	}
 
 	do {
-		unsigned long index;
-		unsigned long offset;
-		unsigned long maxlen;
-		size_t copied;
+		pgoff_t index;		/* Pagecache index for current page */
+		unsigned long offset;	/* Offset into pagecache page */
+		unsigned long maxlen;	/* Bytes remaining in current iovec */
+		size_t bytes;		/* Bytes to write to page */
+		size_t copied;		/* Bytes copied from user */
 
-		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+		offset = (pos & (PAGE_CACHE_SIZE - 1));
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
 		if (bytes > count)
 			bytes = count;
 
+		maxlen = cur_iov->iov_len - iov_offset;
+		if (maxlen > bytes)
+			maxlen = bytes;
+
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		maxlen = cur_iov->iov_len - iov_base;
-		if (maxlen > bytes)
-			maxlen = bytes;
 		fault_in_pages_readable(buf, maxlen);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);

@@ -2019,7 +2020,7 @@ generic_file_buffered_write(struct kiocb
 							buf, bytes);
 		else
 			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_base, bytes);
+						cur_iov, iov_offset, bytes);
 		flush_dcache_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (status == AOP_TRUNCATED_PAGE) {

@@ -2037,12 +2038,12 @@ generic_file_buffered_write(struct kiocb
 				buf += status;
 				if (unlikely(nr_segs > 1)) {
 					filemap_set_next_iovec(&cur_iov,
-							&iov_base, status);
+							&iov_offset, status);
 					if (count)
 						buf = cur_iov->iov_base +
-							iov_base;
+							iov_offset;
 				} else {
-					iov_base += status;
+					iov_offset += status;
 				}
 			}
 		}

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1984,6 +1984,7 @@ generic_file_buffered_write(struct kiocb
 		if (maxlen > bytes)
 			maxlen = bytes;
 
+#ifndef CONFIG_DEBUG_VM
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the

@@ -1991,6 +1992,7 @@ generic_file_buffered_write(struct kiocb
 		 * up-to-date.
 		 */
 		fault_in_pages_readable(buf, maxlen);
+#endif
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -2001,22 +2001,9 @@ generic_file_buffered_write(struct kiocb
 		}
 
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
-		if (unlikely(status)) {
-			loff_t isize = i_size_read(inode);
+		if (unlikely(status))
+			goto fs_write_aop_error;
 
-			if (status != AOP_TRUNCATED_PAGE)
-				unlock_page(page);
-			page_cache_release(page);
-			if (status == AOP_TRUNCATED_PAGE)
-				continue;
-			/*
-			 * prepare_write() may have instantiated a few blocks
-			 * outside i_size.  Trim these off again.
-			 */
-			if (pos + bytes > isize)
-				vmtruncate(inode, isize);
-			break;
-		}
 		if (likely(nr_segs == 1))
 			copied = filemap_copy_from_user(page, offset,
 							buf, bytes);

@@ -2025,40 +2012,53 @@ generic_file_buffered_write(struct kiocb
 						cur_iov, iov_offset, bytes);
 		flush_dcache_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
-		if (status == AOP_TRUNCATED_PAGE) {
-			page_cache_release(page);
-			continue;
+		if (unlikely(status < 0))
+			goto fs_write_aop_error;
+		if (unlikely(copied != bytes)) {
+			status = -EFAULT;
+			goto fs_write_aop_error;
 		}
-		if (likely(copied > 0)) {
-			if (!status)
-				status = copied;
+		if (unlikely(status > 0)) /* filesystem did partial write */
+			copied = status;
 
-			if (status >= 0) {
-				written += status;
-				count -= status;
-				pos += status;
-				buf += status;
-				if (unlikely(nr_segs > 1)) {
-					filemap_set_next_iovec(&cur_iov,
-							&iov_offset, status);
-					if (count)
-						buf = cur_iov->iov_base +
-							iov_offset;
-				} else {
-					iov_offset += status;
-				}
+		if (likely(copied > 0)) {
+			written += copied;
+			count -= copied;
+			pos += copied;
+			buf += copied;
+			if (unlikely(nr_segs > 1)) {
+				filemap_set_next_iovec(&cur_iov,
+						&iov_offset, copied);
+				if (count)
+					buf = cur_iov->iov_base + iov_offset;
+			} else {
+				iov_offset += copied;
 			}
 		}
-		if (unlikely(copied != bytes))
-			if (status >= 0)
-				status = -EFAULT;
 		unlock_page(page);
 		mark_page_accessed(page);
 		page_cache_release(page);
-		if (status < 0)
-			break;
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
+		continue;
+
+fs_write_aop_error:
+		if (status != AOP_TRUNCATED_PAGE)
+			unlock_page(page);
+		page_cache_release(page);
+
+		/*
+		 * prepare_write() may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 */
+		if (pos + bytes > inode->i_size)
+			vmtruncate(inode, inode->i_size);
+		if (status == AOP_TRUNCATED_PAGE)
+			continue;
+		else
+			break;
+
 	} while (count);
 	*ppos = pos;
 

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -689,26 +689,22 @@ EXPORT_SYMBOL(probe_page);
 struct page *find_or_create_page(struct address_space *mapping,
 		unsigned long index, gfp_t gfp_mask)
 {
-	struct page *page, *cached_page = NULL;
+	struct page *page;
 	int err;
 repeat:
 	page = find_lock_page(mapping, index);
 	if (!page) {
-		if (!cached_page) {
-			cached_page = alloc_page(gfp_mask);
-			if (!cached_page)
-				return NULL;
-		}
-		err = add_to_page_cache_lru(cached_page, mapping,
-					index, gfp_mask);
-		if (!err) {
-			page = cached_page;
-			cached_page = NULL;
-		} else if (err == -EEXIST)
-			goto repeat;
+		page = alloc_page(gfp_mask);
+		if (!page)
+			return NULL;
+		err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
+		if (unlikely(err)) {
+			page_cache_release(page);
+			page = NULL;
+			if (err == -EEXIST)
+				goto repeat;
+		}
 	}
-	if (cached_page)
-		page_cache_release(cached_page);
 	return page;
 }
 EXPORT_SYMBOL(find_or_create_page);

@@ -903,11 +899,9 @@ void do_generic_mapping_read(struct addr
 	unsigned long next_index;
 	unsigned long prev_index;
 	loff_t isize;
-	struct page *cached_page;
 	int error;
 	struct file_ra_state ra = *_ra;
 
-	cached_page = NULL;
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
 	prev_index = ra.prev_page;

@@ -1084,23 +1078,20 @@ no_cached_page:
 		 * Ok, it wasn't cached, so we need to create a new
 		 * page..
 		 */
-		if (!cached_page) {
-			cached_page = page_cache_alloc_cold(mapping);
-			if (!cached_page) {
-				desc->error = -ENOMEM;
-				goto out;
-			}
+		page = page_cache_alloc_cold(mapping);
+		if (!page) {
+			desc->error = -ENOMEM;
+			goto out;
 		}
-		error = add_to_page_cache_lru(cached_page, mapping,
+		error = add_to_page_cache_lru(page, mapping,
 						index, GFP_KERNEL);
 		if (error) {
+			page_cache_release(page);
 			if (error == -EEXIST)
 				goto find_page;
 			desc->error = error;
 			goto out;
 		}
-		page = cached_page;
-		cached_page = NULL;
 		goto readpage;
 	}
 

@@ -1110,8 +1101,6 @@ out:
 		_ra->prev_page = prev_index;
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
-	if (cached_page)
-		page_cache_release(cached_page);
 	if (filp)
 		file_accessed(filp);
 }

@@ -1605,35 +1594,28 @@ static struct page *__read_cache_page(st
 				int (*filler)(void *,struct page*),
 				void *data)
 {
-	struct page *page, *cached_page = NULL;
+	struct page *page;
 	int err;
 repeat:
 	page = find_get_page(mapping, index);
 	if (!page) {
-		if (!cached_page) {
-			cached_page = page_cache_alloc_cold(mapping);
-			if (!cached_page)
-				return ERR_PTR(-ENOMEM);
-		}
-		err = add_to_page_cache_lru(cached_page, mapping,
-					index, GFP_KERNEL);
-		if (err == -EEXIST)
-			goto repeat;
-		if (err < 0) {
+		page = page_cache_alloc_cold(mapping);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+		if (unlikely(err)) {
+			page_cache_release(page);
+			if (err == -EEXIST)
+				goto repeat;
 			/* Presumably ENOMEM for radix tree node */
-			page_cache_release(cached_page);
 			return ERR_PTR(err);
 		}
-		page = cached_page;
-		cached_page = NULL;
 		err = filler(data, page);
 		if (err < 0) {
 			page_cache_release(page);
 			page = ERR_PTR(err);
 		}
 	}
-	if (cached_page)
-		page_cache_release(cached_page);
 	return page;
 }
 

@@ -1711,40 +1693,6 @@ struct page *read_cache_page(struct addr
 EXPORT_SYMBOL(read_cache_page);
 
 /*
- * If the page was newly created, increment its refcount and add it to the
- * caller's lru-buffering pagevec.  This function is specifically for
- * generic_file_write().
- */
-static inline struct page *
-__grab_cache_page(struct address_space *mapping, unsigned long index,
-			struct page **cached_page, struct pagevec *lru_pvec)
-{
-	int err;
-	struct page *page;
-repeat:
-	page = find_lock_page(mapping, index);
-	if (!page) {
-		if (!*cached_page) {
-			*cached_page = page_cache_alloc(mapping);
-			if (!*cached_page)
-				return NULL;
-		}
-		err = add_to_page_cache(*cached_page, mapping,
-					index, GFP_KERNEL);
-		if (err == -EEXIST)
-			goto repeat;
-		if (err == 0) {
-			page = *cached_page;
-			page_cache_get(page);
-			if (!pagevec_add(lru_pvec, page))
-				__pagevec_lru_add(lru_pvec);
-			*cached_page = NULL;
-		}
-	}
-	return page;
-}
-
-/*
  * The logic we want is
  *
  *	if suid or (sgid and xgrp)

@@ -1938,6 +1886,33 @@ generic_file_direct_write(struct kiocb *
 }
 EXPORT_SYMBOL(generic_file_direct_write);
 
+/*
+ * Find or create a page at the given pagecache position. Return the locked
+ * page. This function is specifically for buffered writes.
+ */
+static struct page *__grab_cache_page(struct address_space *mapping,
+							pgoff_t index)
+{
+	int status;
+	struct page *page;
+repeat:
+	page = find_lock_page(mapping, index);
+	if (likely(page))
+		return page;
+
+	page = page_cache_alloc(mapping);
+	if (!page)
+		return NULL;
+	status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+	if (unlikely(status)) {
+		page_cache_release(page);
+		if (status == -EEXIST)
+			goto repeat;
+		return NULL;
+	}
+	return page;
+}
+
 ssize_t
 generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos, loff_t *ppos,

@@ -1948,15 +1923,10 @@ generic_file_buffered_write(struct kiocb
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	struct inode 	*inode = mapping->host;
 	long		status = 0;
-	struct page	*page;
-	struct page	*cached_page = NULL;
-	struct pagevec	lru_pvec;
 	const struct iovec *cur_iov = iov; /* current iovec */
 	size_t		iov_offset = 0;	   /* offset in the current iovec */
 	char __user	*buf;
 
-	pagevec_init(&lru_pvec, 0);
-
 	/*
 	 * handle partial DIO write.  Adjust cur_iov if needed.
 	 */

@@ -1968,6 +1938,7 @@ generic_file_buffered_write(struct kiocb
 	}
 
 	do {
+		struct page *page;
 		pgoff_t index;		/* Pagecache index for current page */
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long maxlen;	/* Bytes remaining in current iovec */

@@ -1994,7 +1965,8 @@ generic_file_buffered_write(struct kiocb
 		fault_in_pages_readable(buf, maxlen);
 #endif
 
-		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
+
+		page = __grab_cache_page(mapping, index);
 		if (!page) {
 			status = -ENOMEM;
 			break;

@@ -2062,9 +2034,6 @@ fs_write_aop_error:
 	} while (count);
 	*ppos = pos;
 
-	if (cached_page)
-		page_cache_release(cached_page);
-
 	/*
 	 * For now, when the user asks for O_SYNC, we'll actually give O_DSYNC
 	 */

@@ -2084,7 +2053,6 @@ fs_write_aop_error:
 	if (unlikely(file->f_flags & O_DIRECT) && written)
 		status = filemap_write_and_wait(mapping);
 
-	pagevec_lru_add(&lru_pvec);
 	return written ? written : status;
 }
 EXPORT_SYMBOL(generic_file_buffered_write);

Index: linux-2.6/fs/mpage.c
===================================================================
@@ -389,33 +389,25 @@ mpage_readpages(struct address_space *ma
 	struct bio *bio = NULL;
 	unsigned page_idx;
 	sector_t last_block_in_bio = 0;
-	struct pagevec lru_pvec;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
 
 	clear_buffer_mapped(&map_bh);
-	pagevec_init(&lru_pvec, 0);
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_entry(pages->prev, struct page, lru);
 
 		prefetchw(&page->flags);
 		list_del(&page->lru);
-		if (!add_to_page_cache(page, mapping,
+		if (!add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
 			bio = do_mpage_readpage(bio, page,
 					nr_pages - page_idx,
 					&last_block_in_bio, &map_bh,
 					&first_logical_block,
 					get_block);
-			if (!pagevec_add(&lru_pvec, page)) {
-				cond_resched();
-				__pagevec_lru_add(&lru_pvec);
-			}
-		} else {
-			page_cache_release(page);
 		}
+		page_cache_release(page);
 	}
-	pagevec_lru_add(&lru_pvec);
 	BUG_ON(!list_empty(pages));
 	if (bio)
 		mpage_bio_submit(READ, bio);

Index: linux-2.6/mm/readahead.c
===================================================================
@@ -230,30 +230,25 @@ int read_cache_pages(struct address_spac
 			int (*filler)(void *, struct page *), void *data)
 {
 	struct page *page;
-	struct pagevec lru_pvec;
 	int ret = 0;
 
-	pagevec_init(&lru_pvec, 0);
-
 	while (!list_empty(pages)) {
 		page = list_to_page(pages);
 		list_del(&page->lru);
-		if (add_to_page_cache(page, mapping, page->index, GFP_KERNEL)) {
+		if (add_to_page_cache_lru(page, mapping,
+					page->index, GFP_KERNEL)) {
 			page_cache_release(page);
 			continue;
 		}
+		page_cache_release(page);
+
 		ret = filler(data, page);
-		if (!pagevec_add(&lru_pvec, page)) {
-			cond_resched();
-			__pagevec_lru_add(&lru_pvec);
-		}
-		if (ret) {
+		if (unlikely(ret)) {
 			put_pages_list(pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);
 	}
-	pagevec_lru_add(&lru_pvec);
 	return ret;
 }
 

@@ -263,7 +258,6 @@ static int read_pages(struct address_spa
 		struct list_head *pages, unsigned nr_pages)
 {
 	unsigned page_idx;
-	struct pagevec lru_pvec;
 	int ret;
 
 	if (mapping->a_ops->readpages) {

@@ -273,21 +267,15 @@ static int read_pages(struct address_spa
 		goto out;
 	}
 
-	pagevec_init(&lru_pvec, 0);
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_to_page(pages);
 		list_del(&page->lru);
-		if (!add_to_page_cache(page, mapping,
+		if (!add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
 			mapping->a_ops->readpage(filp, page);
-			if (!pagevec_add(&lru_pvec, page)) {
-				cond_resched();
-				__pagevec_lru_add(&lru_pvec);
-			}
-		} else
-			page_cache_release(page);
+		}
+		page_cache_release(page);
 	}
-	pagevec_lru_add(&lru_pvec);
 	ret = 0;
 out:
 	return ret;

Index: linux-2.6/mm/filemap.h
===================================================================
@@ -22,82 +22,82 @@ __filemap_copy_from_user_iovec_inatomic(
 
 /*
  * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then clear the page
- * out to (offset+bytes) and return the number of bytes which were copied.
- *
- * NOTE: For this to work reliably we really want copy_from_user_inatomic_nocache
- * to *NOT* zero any tail of the buffer that it failed to copy.  If it does,
- * and if the following non-atomic copy succeeds, then there is a small window
- * where the target page contains neither the data before the write, nor the
- * data after the write (it contains zero).  A read at this time will see
- * data that is inconsistent with any ordering of the read and the write.
- * (This has been detected in practice).
+ * were sucessfully copied.  If a fault is encountered then return the number of
+ * bytes which were copied.
  */
 static inline size_t
-filemap_copy_from_user(struct page *page, unsigned long offset,
-			const char __user *buf, unsigned bytes)
+filemap_copy_from_user_atomic(struct page *page, unsigned long offset,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t base, size_t bytes)
 {
 	char *kaddr;
-	int left;
+	size_t copied;
 
 	kaddr = kmap_atomic(page, KM_USER0);
-	left = __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
+	if (likely(nr_segs == 1)) {
+		int left;
+		char __user *buf = iov->iov_base + base;
+		left = __copy_from_user_inatomic_nocache(kaddr + offset,
+							buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset,
+							iov, base, bytes);
+	}
 	kunmap_atomic(kaddr, KM_USER0);
 
-	if (left != 0) {
-		/* Do it the slow way */
-		kaddr = kmap(page);
-		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
-		kunmap(page);
-	}
-	return bytes - left;
+	return copied;
 }
 
 /*
- * This has the same sideeffects and return value as filemap_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
- * single-segment behaviour.
+ * This has the same sideeffects and return value as
+ * filemap_copy_from_user_atomic().
+ * The difference is that it attempts to resolve faults.
  */
 static inline size_t
-filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
-			const struct iovec *iov, size_t base, size_t bytes)
+filemap_copy_from_user(struct page *page, unsigned long offset,
+			const struct iovec *iov, unsigned long nr_segs,
+			 size_t base, size_t bytes)
 {
 	char *kaddr;
 	size_t copied;
 
-	kaddr = kmap_atomic(page, KM_USER0);
-	copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov,
-							 base, bytes);
-	kunmap_atomic(kaddr, KM_USER0);
-	if (copied != bytes) {
-		kaddr = kmap(page);
-		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov,
-								 base, bytes);
-		if (bytes - copied)
-			memset(kaddr + offset + copied, 0, bytes - copied);
-		kunmap(page);
+	kaddr = kmap(page);
+	if (likely(nr_segs == 1)) {
+		int left;
+		char __user *buf = iov->iov_base + base;
+		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset,
+							iov, base, bytes);
 	}
+	kunmap(page);
 	return copied;
 }
 
 static inline void
-filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
+filemap_set_next_iovec(const struct iovec **iovp, unsigned long nr_segs,
+						 size_t *basep, size_t bytes)
 {
-	const struct iovec *iov = *iovp;
-	size_t base = *basep;
-
-	while (bytes) {
-		int copy = min(bytes, iov->iov_len - base);
-
-		bytes -= copy;
-		base += copy;
-		if (iov->iov_len == base) {
-			iov++;
-			base = 0;
+	if (likely(nr_segs == 1)) {
+		*basep += bytes;
+	} else {
+		const struct iovec *iov = *iovp;
+		size_t base = *basep;
+
+		while (bytes) {
+			int copy = min(bytes, iov->iov_len - base);
+
+			bytes -= copy;
+			base += copy;
+			if (iov->iov_len == base) {
+				iov++;
+				base = 0;
+			}
 		}
+		*iovp = iov;
+		*basep = base;
 	}
-	*iovp = iov;
-	*basep = base;
 }
 #endif

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1930,12 +1930,7 @@ generic_file_buffered_write(struct kiocb
 	/*
 	 * handle partial DIO write.  Adjust cur_iov if needed.
 	 */
-	if (likely(nr_segs == 1))
-		buf = iov->iov_base + written;
-	else {
-		filemap_set_next_iovec(&cur_iov, &iov_offset, written);
-		buf = cur_iov->iov_base + iov_offset;
-	}
+	filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, written);
 
 	do {
 		struct page *page;

@@ -1945,6 +1940,7 @@ generic_file_buffered_write(struct kiocb
 		size_t bytes;		/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
+		buf = cur_iov->iov_base + iov_offset;
 		offset = (pos & (PAGE_CACHE_SIZE - 1));
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;

@@ -1976,13 +1972,10 @@ generic_file_buffered_write(struct kiocb
 		if (unlikely(status))
 			goto fs_write_aop_error;
 
-		if (likely(nr_segs == 1))
-			copied = filemap_copy_from_user(page, offset,
-							buf, bytes);
-		else
-			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_offset, bytes);
+		copied = filemap_copy_from_user(page, offset,
+					cur_iov, nr_segs, iov_offset, bytes);
 		flush_dcache_page(page);
+
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (unlikely(status < 0))
 			goto fs_write_aop_error;

@@ -1993,20 +1986,11 @@ generic_file_buffered_write(struct kiocb
 		if (unlikely(status > 0)) /* filesystem did partial write */
 			copied = status;
 
-		if (likely(copied > 0)) {
-			written += copied;
-			count -= copied;
-			pos += copied;
-			buf += copied;
-			if (unlikely(nr_segs > 1)) {
-				filemap_set_next_iovec(&cur_iov,
-						&iov_offset, copied);
-				if (count)
-					buf = cur_iov->iov_base + iov_offset;
-			} else {
-				iov_offset += copied;
-			}
-		}
+		written += copied;
+		count -= copied;
+		pos += copied;
+		filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, copied);
+
 		unlock_page(page);
 		mark_page_accessed(page);
 		page_cache_release(page);

Index: linux-2.6/mm/filemap_xip.c
===================================================================
@@ -14,7 +14,6 @@
 #include <linux/uio.h>
 #include <linux/rmap.h>
 #include <asm/tlbflush.h>
-#include "filemap.h"
 
 /*
  * We do use our own empty page to avoid interference with other users

@@ -318,6 +317,7 @@ __xip_file_write(struct file *filp, cons
 		unsigned long index;
 		unsigned long offset;
 		size_t copied;
+		char *kaddr;
 
 		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
 		index = pos >> PAGE_CACHE_SHIFT;

@@ -325,14 +325,6 @@ __xip_file_write(struct file *filp, cons
 		if (bytes > count)
 			bytes = count;
 
-		/*
-		 * Bring in the user page that we will copy from _first_.
-		 * Otherwise there's a nasty deadlock on copying from the
-		 * same page as we're writing to, without it being marked
-		 * up-to-date.
-		 */
-		fault_in_pages_readable(buf, bytes);
-
 		page = a_ops->get_xip_page(mapping,
 					   index*(PAGE_SIZE/512), 0);
 		if (IS_ERR(page) && (PTR_ERR(page) == -ENODATA)) {

@@ -349,8 +341,13 @@ __xip_file_write(struct file *filp, cons
 			break;
 		}
 
-		copied = filemap_copy_from_user(page, offset, buf, bytes);
+		fault_in_pages_readable(buf, bytes);
+		kaddr = kmap_atomic(page, KM_USER0);
+		copied = bytes -
+			__copy_from_user_inatomic_nocache(kaddr, buf, bytes);
+		kunmap_atomic(kaddr, KM_USER0);
 		flush_dcache_page(page);
+
 		if (likely(copied > 0)) {
 			status = copied;
 

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1933,11 +1933,12 @@ generic_file_buffered_write(struct kiocb
 	filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, written);
 
 	do {
+		struct page *src_page;
 		struct page *page;
 		pgoff_t index;		/* Pagecache index for current page */
 		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long maxlen;	/* Bytes remaining in current iovec */
-		size_t bytes;		/* Bytes to write to page */
+		unsigned long seglen;	/* Bytes remaining in current iovec */
+		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
 		buf = cur_iov->iov_base + iov_offset;

@@ -1947,20 +1948,30 @@ generic_file_buffered_write(struct kiocb
 		if (bytes > count)
 			bytes = count;
 
-		maxlen = cur_iov->iov_len - iov_offset;
-		if (maxlen > bytes)
-			maxlen = bytes;
+		/*
+		 * a non-NULL src_page indicates that we're doing the
+		 * copy via get_user_pages and kmap.
+		 */
+		src_page = NULL;
+
+		seglen = cur_iov->iov_len - iov_offset;
+		if (seglen > bytes)
+			seglen = bytes;
 
-#ifndef CONFIG_DEBUG_VM
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
+		 *
+		 * Not only is this an optimisation, but it is also required
+		 * to check that the address is actually valid, when atomic
+		 * usercopies are used, below.
 		 */
-		fault_in_pages_readable(buf, maxlen);
-#endif
-
+		if (unlikely(fault_in_pages_readable(buf, seglen))) {
+			status = -EFAULT;
+			break;
+		}
 
 		page = __grab_cache_page(mapping, index);
 		if (!page) {

@@ -1968,32 +1979,104 @@ generic_file_buffered_write(struct kiocb
 			break;
 		}
 
+		/*
+		 * non-uptodate pages cannot cope with short copies, and we
+		 * cannot take a pagefault with the destination page locked.
+		 * So pin the source page to copy it.
+		 */
+		if (!PageUptodate(page)) {
+			unlock_page(page);
+
+			src_page = alloc_page(GFP_KERNEL);
+			if (!src_page) {
+				page_cache_release(page);
+				status = -ENOMEM;
+				break;
+			}
+
+			/*
+			 * Cannot get_user_pages with a page locked for the
+			 * same reason as we can't take a page fault with a
+			 * page locked (as explained below).
+			 */
+			copied = filemap_copy_from_user(src_page, offset,
+					cur_iov, nr_segs, iov_offset, bytes);
+			if (unlikely(copied == 0)) {
+				status = -EFAULT;
+				page_cache_release(page);
+				page_cache_release(src_page);
+				break;
+			}
+			bytes = copied;
+
+			lock_page(page);
+			/*
+			 * Can't handle the page going uptodate here, because
+			 * that means we would use non-atomic usercopies, which
+			 * zero out the tail of the page, which can cause
+			 * zeroes to become transiently visible. We could just
+			 * use a non-zeroing copy, but the APIs aren't too
+			 * consistent.
+			 */
+			if (unlikely(!page->mapping || PageUptodate(page))) {
+				unlock_page(page);
+				page_cache_release(page);
+				page_cache_release(src_page);
+				continue;
+			}
+
+		}
+
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
 		if (unlikely(status))
 			goto fs_write_aop_error;
 
-		copied = filemap_copy_from_user(page, offset,
+		if (!src_page) {
+			/*
+			 * Must not enter the pagefault handler here, because
+			 * we hold the page lock, so we might recursively
+			 * deadlock on the same lock, or get an ABBA deadlock
+			 * against a different lock, or against the mmap_sem
+			 * (which nests outside the page lock).  So increment
+			 * preempt count, and use _atomic usercopies.
+			 *
+			 * The page is uptodate so we are OK to encounter a
+			 * short copy: if unmodified parts of the page are
+			 * marked dirty and written out to disk, it doesn't
+			 * really matter.
+			 */
+			pagefault_disable();
+			copied = filemap_copy_from_user_atomic(page, offset,
 					cur_iov, nr_segs, iov_offset, bytes);
+			pagefault_enable();
+		} else {
+			void *src, *dst;
+			src = kmap_atomic(src_page, KM_USER0);
+			dst = kmap_atomic(page, KM_USER1);
+			memcpy(dst + offset, src + offset, bytes);
+			kunmap_atomic(dst, KM_USER1);
+			kunmap_atomic(src, KM_USER0);
+			copied = bytes;
+		}
 		flush_dcache_page(page);
 
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (unlikely(status < 0))
 			goto fs_write_aop_error;
-		if (unlikely(copied != bytes)) {
-			status = -EFAULT;
-			goto fs_write_aop_error;
-		}
 		if (unlikely(status > 0)) /* filesystem did partial write */
-			copied = status;
+			copied = min_t(size_t, copied, status);
+
+		unlock_page(page);
+		mark_page_accessed(page);
+		page_cache_release(page);
+		if (src_page)
+			page_cache_release(src_page);
 
 		written += copied;
 		count -= copied;
 		pos += copied;
 		filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, copied);
 
-		unlock_page(page);
-		mark_page_accessed(page);
-		page_cache_release(page);
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
 		continue;

@@ -2002,6 +2085,8 @@ fs_write_aop_error:
 		if (status != AOP_TRUNCATED_PAGE)
 			unlock_page(page);
 		page_cache_release(page);
+		if (src_page)
+			page_cache_release(src_page);
 
 		/*
 		 * prepare_write() may have instantiated a few blocks

@@ -2014,7 +2099,6 @@ fs_write_aop_error:
 			continue;
 		else
 			break;
-
 	} while (count);
 	*ppos = pos;
 

Index: linux-2.6/include/linux/pagemap.h
===================================================================
@@ -220,6 +220,9 @@ static inline int fault_in_pages_writeab
 {
 	int ret;
 
+	if (unlikely(size == 0))
+		return 0;
+
 	/*
 	 * Writing zeroes into userspace here is OK, because we know that if
 	 * the zero gets there, we'll be overwriting it.

@@ -239,19 +242,23 @@ static inline int fault_in_pages_writeab
 	return ret;
 }
 
-static inline void fault_in_pages_readable(const char __user *uaddr, int size)
+static inline int fault_in_pages_readable(const char __user *uaddr, int size)
 {
 	volatile char c;
 	int ret;
 
+	if (unlikely(size == 0))
+		return 0;
+
 	ret = __get_user(c, uaddr);
 	if (ret == 0) {
 		const char __user *end = uaddr + size - 1;
 
 		if (((unsigned long)uaddr & PAGE_MASK) !=
 				((unsigned long)end & PAGE_MASK))
-		 	__get_user(c, end);
+		 	ret = __get_user(c, end);
 	}
+	return ret;
 }
 
 #endif /* _LINUX_PAGEMAP_H */

Index: linux-2.6/include/linux/fs.h
===================================================================
@@ -398,6 +398,39 @@ struct page;
 struct address_space;
 struct writeback_control;
 
+struct iov_iter {
+	const struct iovec *iov;
+	unsigned long nr_segs;
+	size_t iov_offset;
+	size_t count;
+};
+
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+size_t iov_iter_copy_from_user(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+void iov_iter_advance(struct iov_iter *i, size_t bytes);
+int iov_iter_fault_in_readable(struct iov_iter *i);
+size_t iov_iter_single_seg_count(struct iov_iter *i);
+
+static inline void iov_iter_init(struct iov_iter *i,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t count, size_t written)
+{
+	i->iov = iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count + written;
+
+	iov_iter_advance(i, written);
+}
+
+static inline size_t iov_iter_count(struct iov_iter *i)
+{
+	return i->count;
+}
+
+
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*readpage)(struct file *, struct page *);

218 lines not on this page · raw message

103 lines not on this page · raw message

Index: linux-2.6/fs/buffer.c
===================================================================
@@ -1800,7 +1800,9 @@ static int __block_prepare_write(struct 
 				unmap_underlying_metadata(bh->b_bdev,
 							bh->b_blocknr);
 				if (PageUptodate(page)) {
+					clear_buffer_new(bh);
 					set_buffer_uptodate(bh);
+					mark_buffer_dirty(bh);
 					continue;
 				}
 				if (block_end > to || block_start < from) {

Index: linux-2.6/include/linux/fs.h
===================================================================
@@ -391,6 +391,8 @@ enum positive_aop_returns {
 	AOP_TRUNCATED_PAGE	= 0x80001,
 };
 
+#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
+
 /*
  * oh the beauties of C type declarations.
  */

@@ -451,6 +453,14 @@ struct address_space_operations {
 	 */
 	int (*prepare_write)(struct file *, struct page *, unsigned, unsigned);
 	int (*commit_write)(struct file *, struct page *, unsigned, unsigned);
+
+	int (*write_begin)(struct file *, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned flags,
+				struct page **pagep, void **fsdata);
+	int (*write_end)(struct file *, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata);
+
 	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidatepage) (struct page *, unsigned long);

@@ -465,6 +475,18 @@ struct address_space_operations {
 	int (*launder_page) (struct page *);
 };
 
+/*
+ * pagecache_write_begin/pagecache_write_end must be used by general code
+ * to write into the pagecache.
+ */
+int pagecache_write_begin(struct file *, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned flags,
+				struct page **pagep, void **fsdata);
+
+int pagecache_write_end(struct file *, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata);
+
 struct backing_dev_info;
 struct address_space {
 	struct inode		*host;		/* owner: inode, block_device */

@@ -1969,6 +1991,12 @@ extern int simple_prepare_write(struct f
 			unsigned offset, unsigned to);
 extern int simple_commit_write(struct file *file, struct page *page,
 				unsigned offset, unsigned to);
+extern int simple_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata);
+extern int simple_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata);
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);

300 lines not on this page · raw message

227 lines not on this page · raw message

Index: linux-2.6/include/linux/buffer_head.h
===================================================================
@@ -202,6 +202,16 @@ void block_invalidatepage(struct page *p
 int block_write_full_page(struct page *page, get_block_t *get_block,
 				struct writeback_control *wbc);
 int block_read_full_page(struct page*, get_block_t*);
+int block_write_begin(struct file *, struct address_space *,
+				loff_t, unsigned, unsigned,
+				struct page **, void **, get_block_t*);
+int block_write_end(struct file *, struct address_space *,
+				loff_t, unsigned, unsigned,
+				struct page *, void *);
+int generic_write_end(struct file *, struct address_space *,
+				loff_t, unsigned, unsigned,
+				struct page *, void *);
+void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
 int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
 int cont_prepare_write(struct page*, unsigned, unsigned, get_block_t*,
 				loff_t *);

Index: linux-2.6/include/linux/pagemap.h
===================================================================
@@ -98,6 +98,8 @@ unsigned find_get_pages_contig(struct ad
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 			int tag, unsigned int nr_pages, struct page **pages);
 
+struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index);
+
 /*
  * Returns locked page at given index in given cache, creating it if needed.
  */

62 lines not on this page · raw message

130 lines not on this page · raw message

65 lines not on this page · raw message

99 lines not on this page · raw message

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -2157,7 +2157,7 @@ static ssize_t generic_perform_write_2co
 		 * cannot take a pagefault with the destination page locked.
 		 * So pin the source page to copy it.
 		 */
-		if (!PageUptodate(page)) {
+		if (!PageUptodate(page) && !segment_eq(get_fs(), KERNEL_DS)) {
 			unlock_page(page);
 
 			src_page = alloc_page(GFP_KERNEL);

@@ -2282,6 +2282,13 @@ static ssize_t generic_perform_write(str
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	long status = 0;
 	ssize_t written = 0;
+	unsigned int flags = 0;
+
+	/*
+	 * Copies from kernel address space cannot fail (NFSD is a big user).
+	 */
+	if (segment_eq(get_fs(), KERNEL_DS))
+		flags |= AOP_FLAG_UNINTERRUPTIBLE;
 
 	do {
 		struct page *page;

@@ -2313,7 +2320,7 @@ again:
 			break;
 		}
 
-		status = a_ops->write_begin(file, mapping, pos, bytes, 0,
+		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
 						&page, &fsdata);
 		if (unlikely(status))
 			break;

Index: linux-2.6/mm/shmem.c
===================================================================
@@ -1109,7 +1109,7 @@ static int shmem_getpage(struct inode *i
 	 * Normally, filepage is NULL on entry, and either found
 	 * uptodate immediately, or allocated and zeroed, or read
 	 * in under swappage, which is then assigned to filepage.
-	 * But shmem_prepare_write passes in a locked filepage,
+	 * But shmem_write_begin passes in a locked filepage,
 	 * which may be found not uptodate by other callers too,
 	 * and may need to be copied from the swappage read in.
 	 */

@@ -1454,14 +1454,35 @@ static const struct inode_operations shm
 static const struct inode_operations shmem_symlink_inline_operations;
 
 /*
- * Normally tmpfs makes no use of shmem_prepare_write, but it
+ * Normally tmpfs makes no use of shmem_write_begin, but it
  * lets a tmpfs file be used read-write below the loop driver.
  */
 static int
-shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+shmem_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
+{
+	struct inode *inode = mapping->host;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	*pagep = NULL;
+	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
+}
+
+static int
+shmem_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
 {
-	struct inode *inode = page->mapping->host;
-	return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL);
+	struct inode *inode = mapping->host;
+
+	set_page_dirty(page);
+	mark_page_accessed(page);
+	page_cache_release(page);
+
+	if (pos+copied > inode->i_size)
+		i_size_write(inode, pos+copied);
+
+	return copied;
 }
 
 static ssize_t

@@ -2358,8 +2379,8 @@ static const struct address_space_operat
 	.writepage	= shmem_writepage,
 	.set_page_dirty	= __set_page_dirty_no_writeback,
 #ifdef CONFIG_TMPFS
-	.prepare_write	= shmem_prepare_write,
-	.commit_write	= simple_commit_write,
+	.write_begin	= shmem_write_begin,
+	.write_end	= shmem_write_end,
 #endif
 	.migratepage	= migrate_page,
 };

Index: linux-2.6/fs/configfs/inode.c
===================================================================
@@ -40,8 +40,8 @@ extern struct super_block * configfs_sb;
 
 static const struct address_space_operations configfs_aops = {
 	.readpage	= simple_readpage,
-	.prepare_write	= simple_prepare_write,
-	.commit_write	= simple_commit_write
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
 };
 
 static struct backing_dev_info configfs_backing_dev_info = {

Index: linux-2.6/fs/sysfs/inode.c
===================================================================
@@ -20,8 +20,8 @@ extern struct super_block * sysfs_sb;
 
 static const struct address_space_operations sysfs_aops = {
 	.readpage	= simple_readpage,
-	.prepare_write	= simple_prepare_write,
-	.commit_write	= simple_commit_write
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
 };
 
 static struct backing_dev_info sysfs_backing_dev_info = {

Index: linux-2.6/fs/ramfs/file-mmu.c
===================================================================
@@ -29,8 +29,8 @@
 
 const struct address_space_operations ramfs_aops = {
 	.readpage	= simple_readpage,
-	.prepare_write	= simple_prepare_write,
-	.commit_write	= simple_commit_write,
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
 	.set_page_dirty = __set_page_dirty_no_writeback,
 };
 

Index: linux-2.6/fs/ramfs/file-nommu.c
===================================================================
@@ -29,8 +29,8 @@ static int ramfs_nommu_setattr(struct de
 
 const struct address_space_operations ramfs_aops = {
 	.readpage		= simple_readpage,
-	.prepare_write		= simple_prepare_write,
-	.commit_write		= simple_commit_write,
+	.write_begin		= simple_write_begin,
+	.write_end		= simple_write_end,
 	.set_page_dirty		= __set_page_dirty_no_writeback,
 };
 

Index: linux-2.6/fs/hugetlbfs/inode.c
===================================================================
@@ -159,15 +159,19 @@ static int hugetlbfs_readpage(struct fil
 	return -EINVAL;
 }
 
-static int hugetlbfs_prepare_write(struct file *file,
-			struct page *page, unsigned offset, unsigned to)
+static int hugetlbfs_write_begin(struct file *file,
+			struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
 {
 	return -EINVAL;
 }
 
-static int hugetlbfs_commit_write(struct file *file,
-			struct page *page, unsigned offset, unsigned to)
+static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
 {
+	BUG();
 	return -EINVAL;
 }
 

@@ -539,8 +543,8 @@ static void hugetlbfs_destroy_inode(stru
 
 static const struct address_space_operations hugetlbfs_aops = {
 	.readpage	= hugetlbfs_readpage,
-	.prepare_write	= hugetlbfs_prepare_write,
-	.commit_write	= hugetlbfs_commit_write,
+	.write_begin	= hugetlbfs_write_begin,
+	.write_end	= hugetlbfs_write_end,
 	.set_page_dirty	= hugetlbfs_set_page_dirty,
 };
 

Index: linux-2.6/fs/block_dev.c
===================================================================
@@ -378,14 +378,26 @@ static int blkdev_readpage(struct file *
 	return block_read_full_page(page, blkdev_get_block);
 }
 
-static int blkdev_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to)
-{
-	return block_prepare_write(page, from, to, blkdev_get_block);
+static int blkdev_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
+{
+	*pagep = NULL;
+	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+				blkdev_get_block);
 }
 
-static int blkdev_commit_write(struct file *file, struct page *page, unsigned from, unsigned to)
+static int blkdev_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
 {
-	return block_commit_write(page, from, to);
+	int ret;
+	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	unlock_page(page);
+	page_cache_release(page);
+
+	return ret;
 }
 
 /*

@@ -1333,8 +1345,8 @@ const struct address_space_operations de
 	.readpage	= blkdev_readpage,
 	.writepage	= blkdev_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= blkdev_prepare_write,
-	.commit_write	= blkdev_commit_write,
+	.write_begin	= blkdev_write_begin,
+	.write_end	= blkdev_write_end,
 	.writepages	= generic_writepages,
 	.direct_IO	= blkdev_direct_IO,
 };

Index: linux-2.6/drivers/block/rd.c
===================================================================
@@ -104,50 +104,60 @@ static void make_page_uptodate(struct pa
 		struct buffer_head *head = bh;
 
 		do {
-			if (!buffer_uptodate(bh)) {
-				memset(bh->b_data, 0, bh->b_size);
-				/*
-				 * akpm: I'm totally undecided about this.  The
-				 * buffer has just been magically brought "up to
-				 * date", but nobody should want to be reading
-				 * it anyway, because it hasn't been used for
-				 * anything yet.  It is still in a "not read
-				 * from disk yet" state.
-				 *
-				 * But non-uptodate buffers against an uptodate
-				 * page are against the rules.  So do it anyway.
-				 */
+			if (!buffer_uptodate(bh))
 				 set_buffer_uptodate(bh);
-			}
 		} while ((bh = bh->b_this_page) != head);
-	} else {
-		memset(page_address(page), 0, PAGE_CACHE_SIZE);
 	}
-	flush_dcache_page(page);
 	SetPageUptodate(page);
 }
 
 static int ramdisk_readpage(struct file *file, struct page *page)
 {
-	if (!PageUptodate(page))
+	if (!PageUptodate(page)) {
+		memclear_highpage_flush(page, 0, PAGE_CACHE_SIZE);
 		make_page_uptodate(page);
+	}
 	unlock_page(page);
 	return 0;
 }
 
-static int ramdisk_prepare_write(struct file *file, struct page *page,
-				unsigned offset, unsigned to)
-{
-	if (!PageUptodate(page))
-		make_page_uptodate(page);
+static int ramdisk_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
+{
+	struct page *page;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+
+	page = __grab_cache_page(mapping, index);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
 	return 0;
 }
 
-static int ramdisk_commit_write(struct file *file, struct page *page,
-				unsigned offset, unsigned to)
-{
+static int ramdisk_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
+{
+	if (!PageUptodate(page)) {
+		if (copied != PAGE_CACHE_SIZE) {
+			void *dst;
+			unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+			unsigned to = from + copied;
+
+			dst = kmap_atomic(page, KM_USER0);
+			memset(dst, 0, from);
+			memset(dst + to, 0, PAGE_CACHE_SIZE - to);
+			flush_dcache_page(page);
+			kunmap_atomic(dst, KM_USER0);
+		}
+		make_page_uptodate(page);
+	}
+
 	set_page_dirty(page);
-	return 0;
+	unlock_page(page);
+	page_cache_release(page);
+	return copied;
 }
 
 /*

@@ -191,8 +201,8 @@ static int ramdisk_set_page_dirty(struct
 
 static const struct address_space_operations ramdisk_aops = {
 	.readpage	= ramdisk_readpage,
-	.prepare_write	= ramdisk_prepare_write,
-	.commit_write	= ramdisk_commit_write,
+	.write_begin	= ramdisk_write_begin,
+	.write_end	= ramdisk_write_end,
 	.writepage	= ramdisk_writepage,
 	.set_page_dirty	= ramdisk_set_page_dirty,
 	.writepages	= ramdisk_writepages,

@@ -201,13 +211,14 @@ static const struct address_space_operat
 static int rd_blkdev_pagecache_IO(int rw, struct bio_vec *vec, sector_t sector,
 				struct address_space *mapping)
 {
-	pgoff_t index = sector >> (PAGE_CACHE_SHIFT - 9);
+	loff_t pos = sector << 9;
 	unsigned int vec_offset = vec->bv_offset;
-	int offset = (sector << 9) & ~PAGE_CACHE_MASK;
 	int size = vec->bv_len;
 	int err = 0;
 
 	do {
+		pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+		unsigned offset = pos & ~PAGE_CACHE_MASK;
 		int count;
 		struct page *page;
 		char *src;

@@ -216,40 +227,50 @@ static int rd_blkdev_pagecache_IO(int rw
 		count = PAGE_CACHE_SIZE - offset;
 		if (count > size)
 			count = size;
-		size -= count;
-
-		page = grab_cache_page(mapping, index);
-		if (!page) {
-			err = -ENOMEM;
-			goto out;
-		}
 
-		if (!PageUptodate(page))
-			make_page_uptodate(page);
+		if (rw == WRITE) {
+			err = pagecache_write_begin(NULL, mapping, pos, count,
+							0, &page, NULL);
+			if (err)
+				goto out;
 
-		index++;
+			src = kmap_atomic(vec->bv_page, KM_USER0) + vec_offset;
+			dst = kmap_atomic(page, KM_USER1) + offset;
+		} else {
+again:
+			page = __grab_cache_page(mapping, index);
+			if (!page) {
+				err = -ENOMEM;
+				goto out;
+			}
+			if (!PageUptodate(page)) {
+				mapping->a_ops->readpage(NULL, page);
+				goto again;
+			}
 
-		if (rw == READ) {
 			src = kmap_atomic(page, KM_USER0) + offset;
 			dst = kmap_atomic(vec->bv_page, KM_USER1) + vec_offset;
-		} else {
-			src = kmap_atomic(vec->bv_page, KM_USER0) + vec_offset;
-			dst = kmap_atomic(page, KM_USER1) + offset;
 		}
-		offset = 0;
-		vec_offset += count;
+
 
 		memcpy(dst, src, count);
 
 		kunmap_atomic(src, KM_USER0);
 		kunmap_atomic(dst, KM_USER1);
 
-		if (rw == READ)
+		if (rw == READ) {
 			flush_dcache_page(vec->bv_page);
-		else
-			set_page_dirty(page);
-		unlock_page(page);
-		put_page(page);
+			unlock_page(page);
+			page_cache_release(page);
+		} else {
+			flush_dcache_page(page);
+			pagecache_write_end(NULL, mapping, pos, count,
+							count, page, NULL);
+		}
+
+		pos += count;
+		vec_offset += count;
+		size -= count;
 	} while (size);
 
  out:

Index: linux-2.6/fs/ext2/inode.c
===================================================================
@@ -726,18 +726,21 @@ ext2_readpages(struct file *file, struct
 	return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
 }
 
-static int
-ext2_prepare_write(struct file *file, struct page *page,
-			unsigned from, unsigned to)
+int __ext2_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
 {
-	return block_prepare_write(page,from,to,ext2_get_block);
+	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+							ext2_get_block);
 }
 
 static int
-ext2_nobh_prepare_write(struct file *file, struct page *page,
-			unsigned from, unsigned to)
+ext2_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
 {
-	return nobh_prepare_write(page,from,to,ext2_get_block);
+	*pagep = NULL;
+	return __ext2_write_begin(file, mapping, pos, len, flags, pagep,fsdata);
 }
 
 static int ext2_nobh_writepage(struct page *page,

@@ -773,8 +776,8 @@ const struct address_space_operations ex
 	.readpages		= ext2_readpages,
 	.writepage		= ext2_writepage,
 	.sync_page		= block_sync_page,
-	.prepare_write		= ext2_prepare_write,
-	.commit_write		= generic_commit_write,
+	.write_begin		= ext2_write_begin,
+	.write_end		= generic_write_end,
 	.bmap			= ext2_bmap,
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,

@@ -791,8 +794,7 @@ const struct address_space_operations ex
 	.readpages		= ext2_readpages,
 	.writepage		= ext2_nobh_writepage,
 	.sync_page		= block_sync_page,
-	.prepare_write		= ext2_nobh_prepare_write,
-	.commit_write		= nobh_commit_write,
+	/* XXX: todo */
 	.bmap			= ext2_bmap,
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,

115 lines not on this page · raw message

Index: linux-2.6/fs/ext2/ext2.h
===================================================================
@@ -133,6 +133,9 @@ extern int ext2_get_block(struct inode *
 extern void ext2_truncate (struct inode *);
 extern int ext2_setattr (struct dentry *, struct iattr *);
 extern void ext2_set_inode_flags(struct inode *inode);
+int __ext2_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata);
 
 /* ioctl.c */
 extern int ext2_ioctl (struct inode *, struct file *, unsigned int,

Index: linux-2.6/fs/ext3/inode.c
===================================================================
@@ -1147,51 +1147,68 @@ static int do_journal_get_write_access(h
 	return ext3_journal_get_write_access(handle, bh);
 }
 
-static int ext3_prepare_write(struct file *file, struct page *page,
-			      unsigned from, unsigned to)
+static int ext3_write_begin(struct file *file, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned flags,
+				struct page **pagep, void **fsdata)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = mapping->host;
 	int ret, needed_blocks = ext3_writepage_trans_blocks(inode);
 	handle_t *handle;
 	int retries = 0;
+	struct page *page;
+	pgoff_t index;
+	unsigned from, to;
+
+	index = pos >> PAGE_CACHE_SHIFT;
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
 
 retry:
+	page = __grab_cache_page(mapping, index);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
+
 	handle = ext3_journal_start(inode, needed_blocks);
 	if (IS_ERR(handle)) {
+		unlock_page(page);
+		page_cache_release(page);
 		ret = PTR_ERR(handle);
 		goto out;
 	}
-	if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
-		ret = nobh_prepare_write(page, from, to, ext3_get_block);
-	else
-		ret = block_prepare_write(page, from, to, ext3_get_block);
+	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+							ext3_get_block);
 	if (ret)
-		goto prepare_write_failed;
+		goto write_begin_failed;
 
 	if (ext3_should_journal_data(inode)) {
 		ret = walk_page_buffers(handle, page_buffers(page),
 				from, to, NULL, do_journal_get_write_access);
 	}
-prepare_write_failed:
-	if (ret)
+write_begin_failed:
+	if (ret) {
 		ext3_journal_stop(handle);
+		unlock_page(page);
+		page_cache_release(page);
+	}
 	if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 out:
 	return ret;
 }
 
+
 int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
 {
 	int err = journal_dirty_data(handle, bh);
 	if (err)
 		ext3_journal_abort_handle(__FUNCTION__, __FUNCTION__,
-						bh, handle,err);
+						bh, handle, err);
 	return err;
 }
 
-/* For commit_write() in data=journal mode */
-static int commit_write_fn(handle_t *handle, struct buffer_head *bh)
+/* For write_end() in data=journal mode */
+static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 {
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;

@@ -1206,78 +1223,100 @@ static int commit_write_fn(handle_t *han
  * ext3 never places buffers on inode->i_mapping->private_list.  metadata
  * buffers are managed internally.
  */
-static int ext3_ordered_commit_write(struct file *file, struct page *page,
-			     unsigned from, unsigned to)
+static int ext3_ordered_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext3_journal_current_handle();
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = file->f_mapping->host;
+	unsigned from, to;
 	int ret = 0, ret2;
 
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
 	ret = walk_page_buffers(handle, page_buffers(page),
 		from, to, NULL, ext3_journal_dirty_data);
 
 	if (ret == 0) {
 		/*
-		 * generic_commit_write() will run mark_inode_dirty() if i_size
+		 * generic_write_end() will run mark_inode_dirty() if i_size
 		 * changes.  So let's piggyback the i_disksize mark_inode_dirty
 		 * into that.
 		 */
 		loff_t new_i_size;
 
-		new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+		new_i_size = pos + copied;
 		if (new_i_size > EXT3_I(inode)->i_disksize)
 			EXT3_I(inode)->i_disksize = new_i_size;
-		ret = generic_commit_write(file, page, from, to);
+		copied = generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+		if (copied < 0)
+			ret = copied;
+	} else {
+		unlock_page(page);
+		page_cache_release(page);
 	}
 	ret2 = ext3_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
-static int ext3_writeback_commit_write(struct file *file, struct page *page,
-			     unsigned from, unsigned to)
+static int ext3_writeback_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext3_journal_current_handle();
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = file->f_mapping->host;
 	int ret = 0, ret2;
 	loff_t new_i_size;
 
-	new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	new_i_size = pos + copied;
 	if (new_i_size > EXT3_I(inode)->i_disksize)
 		EXT3_I(inode)->i_disksize = new_i_size;
 
-	if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
-		ret = nobh_commit_write(file, page, from, to);
-	else
-		ret = generic_commit_write(file, page, from, to);
+	copied = generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+	if (copied < 0)
+		ret = copied;
 
 	ret2 = ext3_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
-static int ext3_journalled_commit_write(struct file *file,
-			struct page *page, unsigned from, unsigned to)
+static int ext3_journalled_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext3_journal_current_handle();
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 	int partial = 0;
-	loff_t pos;
+	unsigned from, to;
 
-	/*
-	 * Here we duplicate the generic_commit_write() functionality
-	 */
-	pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
+	if (copied < len) {
+		if (!PageUptodate(page))
+			copied = 0;
+		page_zero_new_buffers(page, from+copied, to);
+	}
 
 	ret = walk_page_buffers(handle, page_buffers(page), from,
-				to, &partial, commit_write_fn);
+				to, &partial, write_end_fn);
 	if (!partial)
 		SetPageUptodate(page);
-	if (pos > inode->i_size)
-		i_size_write(inode, pos);
+	unlock_page(page);
+	page_cache_release(page);
+	if (pos+copied > inode->i_size)
+		i_size_write(inode, pos+copied);
 	EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
 	if (inode->i_size > EXT3_I(inode)->i_disksize) {
 		EXT3_I(inode)->i_disksize = inode->i_size;

@@ -1285,10 +1324,11 @@ static int ext3_journalled_commit_write(
 		if (!ret)
 			ret = ret2;
 	}
+
 	ret2 = ext3_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
 /*

@@ -1546,7 +1586,7 @@ static int ext3_journalled_writepage(str
 			PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
 
 		err = walk_page_buffers(handle, page_buffers(page), 0,
-				PAGE_CACHE_SIZE, NULL, commit_write_fn);
+				PAGE_CACHE_SIZE, NULL, write_end_fn);
 		if (ret == 0)
 			ret = err;
 		EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;

@@ -1706,8 +1746,8 @@ static const struct address_space_operat
 	.readpages	= ext3_readpages,
 	.writepage	= ext3_ordered_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= ext3_prepare_write,
-	.commit_write	= ext3_ordered_commit_write,
+	.write_begin	= ext3_write_begin,
+	.write_end	= ext3_ordered_write_end,
 	.bmap		= ext3_bmap,
 	.invalidatepage	= ext3_invalidatepage,
 	.releasepage	= ext3_releasepage,

@@ -1720,8 +1760,8 @@ static const struct address_space_operat
 	.readpages	= ext3_readpages,
 	.writepage	= ext3_writeback_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= ext3_prepare_write,
-	.commit_write	= ext3_writeback_commit_write,
+	.write_begin	= ext3_write_begin,
+	.write_end	= ext3_writeback_write_end,
 	.bmap		= ext3_bmap,
 	.invalidatepage	= ext3_invalidatepage,
 	.releasepage	= ext3_releasepage,

@@ -1734,8 +1774,8 @@ static const struct address_space_operat
 	.readpages	= ext3_readpages,
 	.writepage	= ext3_journalled_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= ext3_prepare_write,
-	.commit_write	= ext3_journalled_commit_write,
+	.write_begin	= ext3_write_begin,
+	.write_end	= ext3_journalled_write_end,
 	.set_page_dirty	= ext3_journalled_set_page_dirty,
 	.bmap		= ext3_bmap,
 	.invalidatepage	= ext3_invalidatepage,

Index: linux-2.6/fs/ext4/inode.c
===================================================================
@@ -1146,34 +1146,50 @@ static int do_journal_get_write_access(h
 	return ext4_journal_get_write_access(handle, bh);
 }
 
-static int ext4_prepare_write(struct file *file, struct page *page,
-			      unsigned from, unsigned to)
+static int ext4_write_begin(struct file *file, struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned flags,
+				struct page **pagep, void **fsdata)
 {
-	struct inode *inode = page->mapping->host;
+ 	struct inode *inode = mapping->host;
 	int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
 	handle_t *handle;
 	int retries = 0;
+ 	struct page *page;
+ 	pgoff_t index;
+ 	unsigned from, to;
+
+ 	index = pos >> PAGE_CACHE_SHIFT;
+ 	from = pos & (PAGE_CACHE_SIZE - 1);
+ 	to = from + len;
 
 retry:
-	handle = ext4_journal_start(inode, needed_blocks);
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		goto out;
+ 	page = __grab_cache_page(mapping, index);
+ 	if (!page)
+ 		return -ENOMEM;
+ 	*pagep = page;
+
+  	handle = ext4_journal_start(inode, needed_blocks);
+  	if (IS_ERR(handle)) {
+ 		unlock_page(page);
+ 		page_cache_release(page);
+  		ret = PTR_ERR(handle);
+  		goto out;
 	}
-	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
-		ret = nobh_prepare_write(page, from, to, ext4_get_block);
-	else
-		ret = block_prepare_write(page, from, to, ext4_get_block);
-	if (ret)
-		goto prepare_write_failed;
 
-	if (ext4_should_journal_data(inode)) {
+	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+							ext4_get_block);
+
+	if (!ret && ext4_should_journal_data(inode)) {
 		ret = walk_page_buffers(handle, page_buffers(page),
 				from, to, NULL, do_journal_get_write_access);
 	}
-prepare_write_failed:
-	if (ret)
+
+	if (ret) {
 		ext4_journal_stop(handle);
+ 		unlock_page(page);
+ 		page_cache_release(page);
+	}
+
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 out:

@@ -1185,12 +1201,12 @@ int ext4_journal_dirty_data(handle_t *ha
 	int err = jbd2_journal_dirty_data(handle, bh);
 	if (err)
 		ext4_journal_abort_handle(__FUNCTION__, __FUNCTION__,
-						bh, handle,err);
+						bh, handle, err);
 	return err;
 }
 
-/* For commit_write() in data=journal mode */
-static int commit_write_fn(handle_t *handle, struct buffer_head *bh)
+/* For write_end() in data=journal mode */
+static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 {
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;

@@ -1205,78 +1221,100 @@ static int commit_write_fn(handle_t *han
  * ext4 never places buffers on inode->i_mapping->private_list.  metadata
  * buffers are managed internally.
  */
-static int ext4_ordered_commit_write(struct file *file, struct page *page,
-			     unsigned from, unsigned to)
+static int ext4_ordered_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = file->f_mapping->host;
+	unsigned from, to;
 	int ret = 0, ret2;
 
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
 	ret = walk_page_buffers(handle, page_buffers(page),
 		from, to, NULL, ext4_journal_dirty_data);
 
 	if (ret == 0) {
 		/*
-		 * generic_commit_write() will run mark_inode_dirty() if i_size
+		 * generic_write_end() will run mark_inode_dirty() if i_size
 		 * changes.  So let's piggyback the i_disksize mark_inode_dirty
 		 * into that.
 		 */
 		loff_t new_i_size;
 
-		new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+		new_i_size = pos + copied;
 		if (new_i_size > EXT4_I(inode)->i_disksize)
 			EXT4_I(inode)->i_disksize = new_i_size;
-		ret = generic_commit_write(file, page, from, to);
+		copied = generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+		if (copied < 0)
+			ret = copied;
+	} else {
+		unlock_page(page);
+		page_cache_release(page);
 	}
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
-static int ext4_writeback_commit_write(struct file *file, struct page *page,
-			     unsigned from, unsigned to)
+static int ext4_writeback_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = file->f_mapping->host;
 	int ret = 0, ret2;
 	loff_t new_i_size;
 
-	new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	new_i_size = pos + copied;
 	if (new_i_size > EXT4_I(inode)->i_disksize)
 		EXT4_I(inode)->i_disksize = new_i_size;
 
-	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
-		ret = nobh_commit_write(file, page, from, to);
-	else
-		ret = generic_commit_write(file, page, from, to);
+	copied = generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+	if (copied < 0)
+		ret = copied;
 
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
-static int ext4_journalled_commit_write(struct file *file,
-			struct page *page, unsigned from, unsigned to)
+static int ext4_journalled_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 	int partial = 0;
-	loff_t pos;
+	unsigned from, to;
 
-	/*
-	 * Here we duplicate the generic_commit_write() functionality
-	 */
-	pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
+	if (copied < len) {
+		if (!PageUptodate(page))
+			copied = 0;
+		page_zero_new_buffers(page, from+copied, to);
+	}
 
 	ret = walk_page_buffers(handle, page_buffers(page), from,
-				to, &partial, commit_write_fn);
+				to, &partial, write_end_fn);
 	if (!partial)
 		SetPageUptodate(page);
-	if (pos > inode->i_size)
-		i_size_write(inode, pos);
+	unlock_page(page);
+	page_cache_release(page);
+	if (pos+copied > inode->i_size)
+		i_size_write(inode, pos+copied);
 	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
 	if (inode->i_size > EXT4_I(inode)->i_disksize) {
 		EXT4_I(inode)->i_disksize = inode->i_size;

@@ -1284,10 +1322,11 @@ static int ext4_journalled_commit_write(
 		if (!ret)
 			ret = ret2;
 	}
+
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
 /*

@@ -1545,7 +1584,7 @@ static int ext4_journalled_writepage(str
 			PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
 
 		err = walk_page_buffers(handle, page_buffers(page), 0,
-				PAGE_CACHE_SIZE, NULL, commit_write_fn);
+				PAGE_CACHE_SIZE, NULL, write_end_fn);
 		if (ret == 0)
 			ret = err;
 		EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;

@@ -1705,8 +1744,8 @@ static const struct address_space_operat
 	.readpages	= ext4_readpages,
 	.writepage	= ext4_ordered_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= ext4_prepare_write,
-	.commit_write	= ext4_ordered_commit_write,
+	.write_begin	= ext4_write_begin,
+	.write_end	= ext4_ordered_write_end,
 	.bmap		= ext4_bmap,
 	.invalidatepage	= ext4_invalidatepage,
 	.releasepage	= ext4_releasepage,

@@ -1719,8 +1758,8 @@ static const struct address_space_operat
 	.readpages	= ext4_readpages,
 	.writepage	= ext4_writeback_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= ext4_prepare_write,
-	.commit_write	= ext4_writeback_commit_write,
+	.write_begin	= ext4_write_begin,
+	.write_end	= ext4_writeback_write_end,
 	.bmap		= ext4_bmap,
 	.invalidatepage	= ext4_invalidatepage,
 	.releasepage	= ext4_releasepage,

@@ -1733,8 +1772,8 @@ static const struct address_space_operat
 	.readpages	= ext4_readpages,
 	.writepage	= ext4_journalled_writepage,
 	.sync_page	= block_sync_page,
-	.prepare_write	= ext4_prepare_write,
-	.commit_write	= ext4_journalled_commit_write,
+	.write_begin	= ext4_write_begin,
+	.write_end	= ext4_journalled_write_end,
 	.set_page_dirty	= ext4_journalled_set_page_dirty,
 	.bmap		= ext4_bmap,
 	.invalidatepage	= ext4_invalidatepage,

Index: linux-2.6/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
@@ -1414,13 +1414,18 @@ xfs_vm_direct_IO(
 }
 
 STATIC int
-xfs_vm_prepare_write(
+xfs_vm_write_begin(
 	struct file		*file,
-	struct page		*page,
-	unsigned int		from,
-	unsigned int		to)
+	struct address_space	*mapping,
+	loff_t			pos,
+	unsigned		len,
+	unsigned		flags,
+	struct page		**pagep,
+	void			**fsdata)
 {
-	return block_prepare_write(page, from, to, xfs_get_blocks);
+	*pagep = NULL;
+	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+								xfs_get_blocks);
 }
 
 STATIC sector_t

@@ -1474,8 +1479,8 @@ const struct address_space_operations xf
 	.sync_page		= block_sync_page,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
-	.prepare_write		= xfs_vm_prepare_write,
-	.commit_write		= generic_commit_write,
+	.write_begin		= xfs_vm_write_begin,
+	.write_end		= generic_write_end,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= xfs_vm_direct_IO,
 	.migratepage		= buffer_migrate_page,

Index: linux-2.6/fs/xfs/linux-2.6/xfs_lrw.c
===================================================================
@@ -134,45 +134,34 @@ xfs_iozero(
 	loff_t			pos,	/* offset in file		*/
 	size_t			count)	/* size of data to zero		*/
 {
-	unsigned		bytes;
 	struct page		*page;
 	struct address_space	*mapping;
 	int			status;
 
 	mapping = ip->i_mapping;
 	do {
-		unsigned long index, offset;
+		unsigned offset, bytes;
+		void *fsdata;
 
 		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
-		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
 		if (bytes > count)
 			bytes = count;
 
-		status = -ENOMEM;
-		page = grab_cache_page(mapping, index);
-		if (!page)
-			break;
-
-		status = mapping->a_ops->prepare_write(NULL, page, offset,
-							offset + bytes);
+		status = pagecache_write_begin(NULL, mapping, pos, bytes,
+					AOP_FLAG_UNINTERRUPTIBLE,
+					&page, &fsdata);
 		if (status)
-			goto unlock;
+			break;
 
 		memclear_highpage_flush(page, offset, bytes);
 
-		status = mapping->a_ops->commit_write(NULL, page, offset,
-							offset + bytes);
-		if (!status) {
-			pos += bytes;
-			count -= bytes;
-		}
-
-unlock:
-		unlock_page(page);
-		page_cache_release(page);
-		if (status)
-			break;
+		status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
+					page, fsdata);
+		WARN_ON(status <= 0); /* can't return less than zero! */
+		pos += bytes;
+		count -= bytes;
+		status = 0;
 	} while (count);
 
 	return (-status);

Index: linux-2.6/fs/buffer.c
===================================================================
@@ -2027,6 +2027,7 @@ int generic_write_end(struct file *file,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
+	struct inode *inode = mapping->host;
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 
 	unlock_page(page);

@@ -2041,6 +2042,8 @@ int generic_write_end(struct file *file,
 		i_size_write(inode, pos+copied);
 		mark_inode_dirty(inode);
 	}
+
+	return copied;
 }
 EXPORT_SYMBOL(generic_write_end);
 

@@ -2142,14 +2145,14 @@ int block_read_full_page(struct page *pa
 }
 
 /* utility function for filesystems that need to do work on expanding
- * truncates.  Uses prepare/commit_write to allow the filesystem to
+ * truncates.  Uses filesystem pagecache writes to allow the filesystem to
  * deal with the hole.  
  */
-static int __generic_cont_expand(struct inode *inode, loff_t size,
-				 pgoff_t index, unsigned int offset)
+int generic_cont_expand_simple(struct inode *inode, loff_t size)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
+	void *fsdata;
 	unsigned long limit;
 	int err;
 

@@ -2162,146 +2165,141 @@ static int __generic_cont_expand(struct 
 	if (size > inode->i_sb->s_maxbytes)
 		goto out;
 
-	err = -ENOMEM;
-	page = grab_cache_page(mapping, index);
-	if (!page)
-		goto out;
-	err = mapping->a_ops->prepare_write(NULL, page, offset, offset);
-	if (err) {
-		/*
-		 * ->prepare_write() may have instantiated a few blocks
-		 * outside i_size.  Trim these off again.
-		 */
-		unlock_page(page);
-		page_cache_release(page);
-		vmtruncate(inode, inode->i_size);
+	err = pagecache_write_begin(NULL, mapping, size, 0,
+				AOP_FLAG_UNINTERRUPTIBLE|AOP_FLAG_CONT_EXPAND,
+				&page, &fsdata);
+	if (err)
 		goto out;
-	}
 
-	err = mapping->a_ops->commit_write(NULL, page, offset, offset);
+	err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata);
+	BUG_ON(err > 0);
 
-	unlock_page(page);
-	page_cache_release(page);
-	if (err > 0)
-		err = 0;
 out:
 	return err;
 }
 
 int generic_cont_expand(struct inode *inode, loff_t size)
 {
-	pgoff_t index;
 	unsigned int offset;
 
 	offset = (size & (PAGE_CACHE_SIZE - 1)); /* Within page */
 
 	/* ugh.  in prepare/commit_write, if from==to==start of block, we
-	** skip the prepare.  make sure we never send an offset for the start
-	** of a block
-	*/
+	 * skip the prepare.  make sure we never send an offset for the start
+	 * of a block.
+	 * XXX: actually, this should be handled in those filesystems by
+	 * checking for the AOP_FLAG_CONT_EXPAND flag.
+	 */
 	if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) {
 		/* caller must handle this extra byte. */
-		offset++;
+		size++;
 	}
-	index = size >> PAGE_CACHE_SHIFT;
-
-	return __generic_cont_expand(inode, size, index, offset);
+	return generic_cont_expand_simple(inode, size);
 }
 
-int generic_cont_expand_simple(struct inode *inode, loff_t size)
+int cont_expand_zero(struct file *file, struct address_space *mapping,
+			loff_t pos, loff_t *bytes)
 {
-	loff_t pos = size - 1;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	unsigned int offset = (pos & (PAGE_CACHE_SIZE - 1)) + 1;
-
-	/* prepare/commit_write can handle even if from==to==start of block. */
-	return __generic_cont_expand(inode, size, index, offset);
-}
-
-/*
- * For moronic filesystems that do not allow holes in file.
- * We may have to extend the file.
- */
-
-int cont_prepare_write(struct page *page, unsigned offset,
-		unsigned to, get_block_t *get_block, loff_t *bytes)
-{
-	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
-	struct page *new_page;
-	pgoff_t pgpos;
-	long status;
-	unsigned zerofrom;
 	unsigned blocksize = 1 << inode->i_blkbits;
+	struct page *page;
+	void *fsdata;
+	pgoff_t index, curidx;
+	loff_t curpos;
+	unsigned zerofrom, offset, len;
 	void *kaddr;
+	int err = 0;
 
-	while(page->index > (pgpos = *bytes>>PAGE_CACHE_SHIFT)) {
-		status = -ENOMEM;
-		new_page = grab_cache_page(mapping, pgpos);
-		if (!new_page)
-			goto out;
-		/* we might sleep */
-		if (*bytes>>PAGE_CACHE_SHIFT != pgpos) {
-			unlock_page(new_page);
-			page_cache_release(new_page);
-			continue;
-		}
-		zerofrom = *bytes & ~PAGE_CACHE_MASK;
+	index = pos >> PAGE_CACHE_SHIFT;
+	offset = pos & ~PAGE_CACHE_MASK;
+
+	while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) {
+		zerofrom = curpos & ~PAGE_CACHE_MASK;
 		if (zerofrom & (blocksize-1)) {
 			*bytes |= (blocksize-1);
 			(*bytes)++;
 		}
-		status = __block_prepare_write(inode, new_page, zerofrom,
-						PAGE_CACHE_SIZE, get_block);
-		if (status)
-			goto out_unmap;
-		kaddr = kmap_atomic(new_page, KM_USER0);
-		memset(kaddr+zerofrom, 0, PAGE_CACHE_SIZE-zerofrom);
-		flush_dcache_page(new_page);
+		len = PAGE_CACHE_SIZE - zerofrom;
+
+		err = pagecache_write_begin(file, mapping, curpos, len,
+						AOP_FLAG_UNINTERRUPTIBLE,
+						&page, &fsdata);
+		if (err)
+			goto out;
+		kaddr = kmap_atomic(page, KM_USER0);
+		memset(kaddr+zerofrom, 0, len);
+		flush_dcache_page(page);
 		kunmap_atomic(kaddr, KM_USER0);
-		generic_commit_write(NULL, new_page, zerofrom, PAGE_CACHE_SIZE);
-		unlock_page(new_page);
-		page_cache_release(new_page);
+		err = pagecache_write_end(file, mapping, curpos, len, len,
+						page, fsdata);
+		if (err < 0)
+			goto out;
+		BUG_ON(err != len);
+		err = 0;
 	}
 
-	if (page->index < pgpos) {
-		/* completely inside the area */
-		zerofrom = offset;
-	} else {
-		/* page covers the boundary, find the boundary offset */
-		zerofrom = *bytes & ~PAGE_CACHE_MASK;
-
+	/* page covers the boundary, find the boundary offset */
+	if (index == curidx) {
+		zerofrom = curpos & ~PAGE_CACHE_MASK;
 		/* if we will expand the thing last block will be filled */
-		if (to > zerofrom && (zerofrom & (blocksize-1))) {
+		if (offset <= zerofrom) {
+			goto out;
+		}
+		if (zerofrom & (blocksize-1)) {
 			*bytes |= (blocksize-1);
 			(*bytes)++;
 		}
+		len = offset - zerofrom;
 
-		/* starting below the boundary? Nothing to zero out */
-		if (offset <= zerofrom)
-			zerofrom = offset;
-	}
-	status = __block_prepare_write(inode, page, zerofrom, to, get_block);
-	if (status)
-		goto out1;
-	if (zerofrom < offset) {
+		err = pagecache_write_begin(file, mapping, curpos, len,
+						AOP_FLAG_UNINTERRUPTIBLE,
+						&page, &fsdata);
+		if (err)
+			goto out;
 		kaddr = kmap_atomic(page, KM_USER0);
-		memset(kaddr+zerofrom, 0, offset-zerofrom);
+		memset(kaddr+zerofrom, 0, len);
 		flush_dcache_page(page);
 		kunmap_atomic(kaddr, KM_USER0);
-		__block_commit_write(inode, page, zerofrom, offset);
+		err = pagecache_write_end(file, mapping, curpos, len, len,
+						page, fsdata);
+		if (err < 0)
+			goto out;
+		BUG_ON(err != len);
+		err = 0;
 	}
-	return 0;
-out1:
-	ClearPageUptodate(page);
-	return status;
-
-out_unmap:
-	ClearPageUptodate(new_page);
-	unlock_page(new_page);
-	page_cache_release(new_page);
 out:
-	return status;
+	return err;
+}
+
+/*
+ * For moronic filesystems that do not allow holes in file.
+ * We may have to extend the file.
+ */
+int cont_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata,
+			get_block_t *get_block, loff_t *bytes)
+{
+	struct inode *inode = mapping->host;
+	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned zerofrom;
+	int err;
+
+	err = cont_expand_zero(file, mapping, pos, bytes);
+	if (err)
+		goto out;
+
+	zerofrom = *bytes & ~PAGE_CACHE_MASK;
+	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
+		*bytes |= (blocksize-1);
+		(*bytes)++;
+	}
+
+	*pagep = NULL;
+	err = block_write_begin(file, mapping, pos, len,
+				flags, pagep, fsdata, get_block);
+out:
+	return err;
 }
 
 int block_prepare_write(struct page *page, unsigned from, unsigned to,

@@ -3160,7 +3158,7 @@ EXPORT_SYMBOL(block_read_full_page);
 EXPORT_SYMBOL(block_sync_page);
 EXPORT_SYMBOL(block_truncate_page);
 EXPORT_SYMBOL(block_write_full_page);
-EXPORT_SYMBOL(cont_prepare_write);
+EXPORT_SYMBOL(cont_write_begin);
 EXPORT_SYMBOL(end_buffer_read_sync);
 EXPORT_SYMBOL(end_buffer_write_sync);
 EXPORT_SYMBOL(file_fsync);

Index: linux-2.6/include/linux/buffer_head.h
===================================================================
@@ -213,8 +213,9 @@ int generic_write_end(struct file *, str
 				struct page *, void *);
 void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
 int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
-int cont_prepare_write(struct page*, unsigned, unsigned, get_block_t*,
-				loff_t *);
+int cont_write_begin(struct file *, struct address_space *, loff_t,
+			unsigned, unsigned, struct page **, void **,
+			get_block_t *, loff_t *);
 int generic_cont_expand(struct inode *inode, loff_t size);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
 int block_commit_write(struct page *page, unsigned from, unsigned to);

Index: linux-2.6/include/linux/fs.h
===================================================================
@@ -392,6 +392,7 @@ enum positive_aop_returns {
 };
 
 #define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
+#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
 
 /*
  * oh the beauties of C type declarations.

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -1789,6 +1789,7 @@ size_t iov_iter_copy_from_user_atomic(st
 
 	return copied;
 }
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
 
 /*
  * This has the same sideeffects and return value as