Implement new aops for ext3. Probably has some bugs in interaction with
journalling, and corner cases aren't tested/thought out fully, but it
boots and runs. I don't see a fundamental reason why it can't work...
fs/ext3/inode.c | 137 +++++++++++++++++++++++++++++++++++---------------------
1 file changed, 88 insertions(+), 49 deletions(-)
Index: linux-2.6/fs/ext3/inode.c
===================================================================
--- linux-2.6.orig/fs/ext3/inode.c
+++ linux-2.6/fs/ext3/inode.c
@@ -1155,7 +1155,7 @@ 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 ext3_prepare_failure(struct file *file, struct page *page,
+static int ext3_write_failure(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct address_space *mapping;
@@ -1208,29 +1208,40 @@ skip:
return mapping->a_ops->commit_write(file, page, from, block_start);
}
-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, int intr,
+ struct page **pagep, void **fsdata)
{
- struct inode *inode = page->mapping->host;
- int ret, ret2;
+ struct inode *inode = mapping->host;
int needed_blocks = ext3_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;
+
+ page = __grab_cache_page(mapping, index);
+ if (!page)
+ return -ENOMEM;
+ *pagep = page;
retry:
handle = ext3_journal_start(inode, needed_blocks);
if (IS_ERR(handle))
return PTR_ERR(handle);
- 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, intr, pagep, fsdata,
+ ext3_get_block);
if (ret)
goto failure;
if (ext3_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
- from, to, NULL, do_journal_get_write_access);
+ start, end, NULL, do_journal_get_write_access);
if (ret)
/* fatal error, just put the handle and return */
journal_stop(handle);
@@ -1238,7 +1249,7 @@ retry:
return ret;
failure:
- ret2 = ext3_prepare_failure(file, page, from, to);
+ ret2 = ext3_write_failure(file, page, start, end);
if (ret2 < 0)
return ret2;
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
@@ -1247,17 +1258,18 @@ failure:
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;
@@ -1272,78 +1284,103 @@ 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
+ * 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 > EXT3_I(inode)->i_disksize)
EXT3_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 = 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 = block_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 = len;
+ else {
+ /* XXX: don't need to zero new buffers because we abort? */
+ copied = 0;
+ if (!is_handle_aborted(handle))
+ 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);
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;
@@ -1351,10 +1388,12 @@ static int ext3_journalled_commit_write(
if (!ret)
ret = ret2;
}
+
+out:
ret2 = ext3_journal_stop(handle);
if (!ret)
ret = ret2;
- return ret;
+ return ret ? ret : copied;
}
/*
@@ -1612,7 +1651,7 @@ 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;
@@ -1772,8 +1811,8 @@ 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,
@@ -1786,8 +1825,8 @@ 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,
@@ -1800,8 +1839,8 @@ 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,
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
