Re: [ANNOUNCE] new new aops patchset

[Badari Pulavarty <pbadari@gmail.com>]

On Mon, 2007-04-02 at 14:09 +0200, Nick Piggin wrote:
> Updated aops patchset against 2.6.21-rc5.
> 
> http://www.kernel.org/pub/linux/kernel/people/npiggin/patches/new-aops/
> 
> Files/dirs are 2.6.21-rc5-new-aops*

Here is the ext4 support for it. This is a simple port from 
ext3 code. Ran fsx without any problems :)

BTW, I never clearly understood what exactly the problem these
new interfaces are solving and how :( I can dig through the
archives and try to figure out. Would you care to put a 
small description of the *actual* problem and how these
new aops are needed (vs hacking the existing methods).

Thanks,
Badari

---
 fs/ext4/inode.c |  171 +++++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 113 insertions(+), 58 deletions(-)

Index: linux-2.6.21-rc5/fs/ext4/inode.c
===================================================================
--- linux-2.6.21-rc5.orig/fs/ext4/inode.c	2007-03-25 15:56:23.000000000 -0700
+++ linux-2.6.21-rc5/fs/ext4/inode.c	2007-04-03 10:01:34.000000000 -0700
@@ -1154,23 +1154,30 @@ static int do_journal_get_write_access(h
  * This content is expected to be set to zeroes by block_prepare_write().
  * 2006/10/14  SAW
  */
-static int ext4_prepare_failure(struct file *file, struct page *page,
-				unsigned from, unsigned to)
+static int ext4_write_failure(struct file *file, struct address_space *mapping,
+				loff_t pos, unsigned len,
+				struct page *page, void *fsdata)
 {
-	struct address_space *mapping;
 	struct buffer_head *bh, *head, *next;
 	unsigned block_start, block_end;
 	unsigned blocksize;
+	unsigned from, to;
 	int ret;
 	handle_t *handle = ext4_journal_current_handle();
 
-	mapping = page->mapping;
 	if (ext4_should_writeback_data(mapping->host)) {
 		/* optimization: no constraints about data */
+skip_and_stop:
+		ret = ext4_journal_stop(handle);
 skip:
-		return ext4_journal_stop(handle);
+		unlock_page(page);
+		page_cache_release(page);
+		return ret;
 	}
 
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
 	head = page_buffers(page);
 	blocksize = head->b_size;
 	for (	bh = head, block_start = 0;
@@ -1192,7 +1199,7 @@ skip:
 			ret = do_journal_get_write_access(handle, bh);
 			if (ret) {
 				ext4_journal_stop(handle);
-				return ret;
+				goto skip;
 			}
 		}
 	/*
@@ -1201,43 +1208,64 @@ skip:
 	 */
 	}
 	if (block_start <= from)
-		goto skip;
+		goto skip_and_stop;
 
 	/* commit allocated and zeroed buffers */
-	return mapping->a_ops->commit_write(file, page, from, block_start);
+	return mapping->a_ops->write_end(file, mapping, pos, len,
+					block_start - from, page, fsdata);
 }
 
-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;
-	int ret, ret2;
+	struct inode *inode = mapping->host;
 	int needed_blocks = ext4_writepage_trans_blocks(inode);
+	int ret, ret2;
 	handle_t *handle;
 	int retries = 0;
+	struct page *page;
+	pgoff_t index;
+	unsigned start, end;
+
+	index = pos >> PAGE_CACHE_SHIFT;
+	start = pos * (PAGE_CACHE_SIZE - 1);
+	end = start + len;
 
 retry:
+	page = __grab_cache_page(mapping, index);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
+
 	handle = ext4_journal_start(inode, needed_blocks);
-	if (IS_ERR(handle))
+	if (IS_ERR(handle)) {
+		unlock_page(page);
+		page_cache_release(page);
 		return PTR_ERR(handle);
-	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);
+	}
+	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+							ext4_get_block);
 	if (ret)
 		goto failure;
 
 	if (ext4_should_journal_data(inode)) {
 		ret = walk_page_buffers(handle, page_buffers(page),
-				from, to, NULL, do_journal_get_write_access);
-		if (ret)
+				start, end, NULL, do_journal_get_write_access);
+		if (ret) {
 			/* fatal error, just put the handle and return */
 			ext4_journal_stop(handle);
+			unlock_page(page);
+			page_cache_release(page);
+		}
 	}
 	return ret;
 
 failure:
-	ret2 = ext4_prepare_failure(file, page, from, to);
+	ret2 = ext4_write_failure(file, mapping, pos, len, page, *fsdata);
+	/* trim off blocks (XXX: need better helpers than vmtruncate) */
+	if (pos + len > inode->i_size)
+		vmtruncate(inode, inode->i_size);
 	if (ret2 < 0)
 		return ret2;
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -1251,12 +1279,12 @@ 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;
@@ -1271,78 +1299,103 @@ 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
+		 * block_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 = block_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_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 = block_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 = len;
+		else {
+			/* XXX: don't need to zero new buffers because we abort? */
+			copied = 0;
+			if (!is_handle_aborted(handle))
+				jbd2_journal_abort_handle(handle);
+			unlock_page(page);
+			page_cache_release(page);
+			goto out;
+		}
+	}
 
 	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;
@@ -1350,10 +1403,12 @@ static int ext4_journalled_commit_write(
 		if (!ret)
 			ret = ret2;
 	}
+
+out:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	return ret;
+	return ret ? ret : copied;
 }
 
 /*
@@ -1611,7 +1666,7 @@ 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;
@@ -1771,8 +1826,8 @@ 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,
@@ -1785,8 +1840,8 @@ 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,
@@ -1799,8 +1854,8 @@ 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,