[RFC] exofs: New truncate sequence

[Boaz Harrosh <bharrosh@panasas.com>]

These changes are crafted based on the similar
conversion done to ext2 by Nick Piggin.

Please check me out I bound to have miss-looked
something.

- Remove the deprecated ->truncate vector, call a new
  exofs_setsize for on-disk size update, from exofs_setattr
- Call truncate_pagecache on the unused pages if
  write_begin/end fails.
- Cleanup exofs_delete_inode that did stupid inode
  writes and updates on an inode that will be
  removed.
- And finally get rid of exofs_get_block. We never
  had any blocks it was all for calling nobh_truncate_page.
  nobh_truncate_page is not actually needed in exofs since
  the last page is complete and gone just like all the other
  pages. There is no partial blocks in exofs.
  [OK do I might need a partial read here upto i_size ???]

I've tested with this patch, and there are no apparent
failures, so far.

These patches are based on Al's vfs for-next branch, which
contain Nick's last patches. But they do not contain,
(and will lightly conflict with) latest Christoph's
patches. Christoph do you have a tree I can rebase on? or
maybe you want to take this patch into your patchset?

CC: Christoph Hellwig <hch@lst.de>
CC: Nick Piggin <npiggin@suse.de>
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
---
 fs/exofs/exofs.h |    1 -
 fs/exofs/file.c  |    1 -
 fs/exofs/inode.c |  115 +++++++++++++++++++++++++++---------------------------
 3 files changed, 58 insertions(+), 59 deletions(-)

diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 22721b2..0706ce9 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -256,7 +256,6 @@ static inline int exofs_oi_read(struct exofs_i_info *oi,
 }
 
 /* inode.c               */
-void exofs_truncate(struct inode *inode);
 int exofs_setattr(struct dentry *, struct iattr *);
 int exofs_write_begin(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned len, unsigned flags,
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
index fef6899..f9bfe2b 100644
--- a/fs/exofs/file.c
+++ b/fs/exofs/file.c
@@ -86,6 +86,5 @@ const struct file_operations exofs_file_operations = {
 };
 
 const struct inode_operations exofs_file_inode_operations = {
-	.truncate	= exofs_truncate,
 	.setattr	= exofs_setattr,
 };
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 4bb6ef8..1c2666c 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -710,7 +710,7 @@ int exofs_write_begin(struct file *file, struct address_space *mapping,
 					 fsdata);
 		if (ret) {
 			EXOFS_DBGMSG("simple_write_begin faild\n");
-			return ret;
+			goto out;
 		}
 
 		page = *pagep;
@@ -725,7 +725,17 @@ int exofs_write_begin(struct file *file, struct address_space *mapping,
 			EXOFS_DBGMSG("__readpage_filler faild\n");
 		}
 	}
+out:
+	if (unlikely(ret)) {
+		struct inode *inode = mapping->host;
+		loff_t to = pos + len;
 
+		if (to > inode->i_size)
+			truncate_pagecache(inode, to, inode->i_size);
+
+		mark_inode_dirty(inode); /* write the new size */
+		return ret;
+	}
 	return ret;
 }
 
@@ -750,6 +760,10 @@ static int exofs_write_end(struct file *file, struct address_space *mapping,
 	int ret;
 
 	ret = simple_write_end(file, mapping,pos, len, copied, page, fsdata);
+	if (unlikely(ret && pos + len > inode->i_size))
+		truncate_pagecache(inode, pos + len, inode->i_size);
+
+	/* TODO: once simple_write_end marks inode dirty remove */
 	if (i_size != inode->i_size)
 		mark_inode_dirty(inode);
 	return ret;
@@ -808,35 +822,18 @@ static inline int exofs_inode_is_fast_symlink(struct inode *inode)
 	return S_ISLNK(inode->i_mode) && (oi->i_data[0] != 0);
 }
 
-/*
- * get_block_t - Fill in a buffer_head
- * An OSD takes care of block allocation so we just fake an allocation by
- * putting in the inode's sector_t in the buffer_head.
- * TODO: What about the case of create==0 and @iblock does not exist in the
- * object?
- */
-static int exofs_get_block(struct inode *inode, sector_t iblock,
-		    struct buffer_head *bh_result, int create)
-{
-	map_bh(bh_result, inode->i_sb, iblock);
-	return 0;
-}
-
 const struct osd_attr g_attr_logical_length = ATTR_DEF(
 	OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
 
-static int _do_truncate(struct inode *inode)
+static int _do_truncate(struct inode *inode, loff_t newsize)
 {
 	struct exofs_i_info *oi = exofs_i(inode);
-	loff_t isize = i_size_read(inode);
 	int ret;
 
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 
-	nobh_truncate_page(inode->i_mapping, isize, exofs_get_block);
-
-	ret = exofs_oi_truncate(oi, (u64)isize);
-	EXOFS_DBGMSG("(0x%lx) size=0x%llx\n", inode->i_ino, isize);
+	ret = exofs_oi_truncate(oi, (u64)newsize);
+	EXOFS_DBGMSG("(0x%lx) size=0x%llx\n", inode->i_ino, newsize);
 	return ret;
 }
 
@@ -844,35 +841,28 @@ static int _do_truncate(struct inode *inode)
  * Truncate a file to the specified size - all we have to do is set the size
  * attribute.  We make sure the object exists first.
  */
-void exofs_truncate(struct inode *inode)
+static int exofs_setsize(struct inode *inode, loff_t newsize)
 {
-	struct exofs_i_info *oi = exofs_i(inode);
-	int ret;
+	loff_t oldsize;
+	int error;
 
-	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
-	     || S_ISLNK(inode->i_mode)))
-		return;
+	error = inode_newsize_ok(inode, newsize);
+	if (error)
+		return error;
+
+	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	    S_ISLNK(inode->i_mode)))
+		return -EINVAL;
 	if (exofs_inode_is_fast_symlink(inode))
-		return;
+		return -EINVAL;
 	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return;
-
-	/* if we are about to truncate an object, and it hasn't been
-	 * created yet, wait
-	 */
-	if (unlikely(wait_obj_created(oi)))
-		goto fail;
+		return -EPERM;
 
-	ret = _do_truncate(inode);
-	if (ret)
-		goto fail;
+	oldsize = inode->i_size;
+	i_size_write(inode, newsize);
+	truncate_pagecache(inode, oldsize, newsize);
 
-out:
-	mark_inode_dirty(inode);
-	return;
-fail:
-	make_bad_inode(inode);
-	goto out;
+	return _do_truncate(inode, newsize);
 }
 
 /*
@@ -883,11 +873,25 @@ int exofs_setattr(struct dentry *dentry, struct iattr *iattr)
 	struct inode *inode = dentry->d_inode;
 	int error;
 
+	/* if we are about to modify an object, and it hasn't been
+	 * created yet, wait
+	 */
+	error = wait_obj_created(exofs_i(inode));
+	if (unlikely(error))
+		return error;
+
 	error = inode_change_ok(inode, iattr);
 	if (error)
 		return error;
 
-	error = inode_setattr(inode, iattr);
+	if (iattr->ia_valid & ATTR_SIZE) {
+		error = exofs_setsize(inode, iattr->ia_size);
+		if (error)
+			return error;
+	}
+	generic_setattr(inode, iattr);
+	mark_inode_dirty(inode);
+
 	return error;
 }
 
@@ -1335,28 +1339,25 @@ void exofs_delete_inode(struct inode *inode)
 
 	truncate_inode_pages(&inode->i_data, 0);
 
+	/* TODO: should do better here */
 	if (is_bad_inode(inode))
 		goto no_delete;
 
-	mark_inode_dirty(inode);
-	exofs_update_inode(inode, inode_needs_sync(inode));
-
 	inode->i_size = 0;
-	if (inode->i_blocks)
-		exofs_truncate(inode);
-
 	clear_inode(inode);
 
-	ret = exofs_get_io_state(&sbi->layout, &ios);
-	if (unlikely(ret)) {
-		EXOFS_ERR("%s: exofs_get_io_state failed\n", __func__);
-		return;
-	}
-
 	/* if we are deleting an obj that hasn't been created yet, wait */
 	if (!obj_created(oi)) {
 		BUG_ON(!obj_2bcreated(oi));
 		wait_event(oi->i_wq, obj_created(oi));
+		/* ignore the error attempt a remove anyway */
+	}
+
+	/* Now Remove the OSD objects */
+	ret = exofs_get_io_state(&sbi->layout, &ios);
+	if (unlikely(ret)) {
+		EXOFS_ERR("%s: exofs_get_io_state failed\n", __func__);
+		return;
 	}
 
 	ios->obj.id = exofs_oi_objno(oi);
-- 
1.6.6.1