Similar to the fsync issue fixed a while ago in commit
2daea67e966dc0c42067ebea015ddac6834cef88 we need to write for data to
actually hit the disk before writing out the metadata to guarantee
data integrity for filesystems that modify the inode in the data I/O
completion path. Currently XFS and NFS handle this manually, and AFS
has a write_inode method that does nothing but waiting for data, while
others are possibly missing out on this.
Fortunately this change has a lot less impact than the fsync change
as none of the write_inode methods starts data writeout of any form
by itself.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Index: linux-2.6/fs/afs/internal.h
===================================================================
--- linux-2.6.orig/fs/afs/internal.h 2010-01-11 15:54:33.776254187 +0100
+++ linux-2.6/fs/afs/internal.h 2010-01-11 15:54:36.556006423 +0100
@@ -733,7 +733,6 @@ extern int afs_write_end(struct file *fi
struct page *page, void *fsdata);
extern int afs_writepage(struct page *, struct writeback_control *);
extern int afs_writepages(struct address_space *, struct writeback_control *);
-extern int afs_write_inode(struct inode *, int);
extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
extern ssize_t afs_file_write(struct kiocb *, const struct iovec *,
unsigned long, loff_t);
Index: linux-2.6/fs/afs/super.c
===================================================================
--- linux-2.6.orig/fs/afs/super.c 2010-01-11 15:54:39.129253854 +0100
+++ linux-2.6/fs/afs/super.c 2010-01-11 15:54:42.315256021 +0100
@@ -48,7 +48,6 @@ struct file_system_type afs_fs_type = {
static const struct super_operations afs_super_ops = {
.statfs = afs_statfs,
.alloc_inode = afs_alloc_inode,
- .write_inode = afs_write_inode,
.destroy_inode = afs_destroy_inode,
.clear_inode = afs_clear_inode,
.put_super = afs_put_super,
Index: linux-2.6/fs/afs/write.c
===================================================================
--- linux-2.6.orig/fs/afs/write.c 2010-01-11 15:54:13.757253993 +0100
+++ linux-2.6/fs/afs/write.c 2010-01-11 15:54:30.085006295 +0100
@@ -585,27 +585,6 @@ int afs_writepages(struct address_space
}
/*
- * write an inode back
- */
-int afs_write_inode(struct inode *inode, int sync)
-{
- struct afs_vnode *vnode = AFS_FS_I(inode);
- int ret;
-
- _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
-
- ret = 0;
- if (sync) {
- ret = filemap_fdatawait(inode->i_mapping);
- if (ret < 0)
- __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
- }
-
- _leave(" = %d", ret);
- return ret;
-}
-
-/*
* completion of write to server
*/
void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
Index: linux-2.6/fs/fs-writeback.c
===================================================================
--- linux-2.6.orig/fs/fs-writeback.c 2010-01-11 15:53:15.462272627 +0100
+++ linux-2.6/fs/fs-writeback.c 2010-01-11 15:54:09.662006283 +0100
@@ -461,15 +461,20 @@ writeback_single_inode(struct inode *ino
ret = do_writepages(mapping, wbc);
- /* Don't write the inode if only I_DIRTY_PAGES was set */
- if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
- int err = write_inode(inode, wait);
+ /*
+ * Make sure to wait on the data before writing out the metadata.
+ * This is important for filesystems that modify metadata on data
+ * I/O completion.
+ */
+ if (wait) {
+ int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
}
- if (wait) {
- int err = filemap_fdatawait(mapping);
+ /* Don't write the inode if only I_DIRTY_PAGES was set */
+ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ int err = write_inode(inode, wait);
if (ret == 0)
ret = err;
}
Index: linux-2.6/fs/nfs/inode.c
===================================================================
--- linux-2.6.orig/fs/nfs/inode.c 2010-01-11 15:54:45.848003872 +0100
+++ linux-2.6/fs/nfs/inode.c 2010-01-11 15:55:13.095006486 +0100
@@ -101,12 +101,7 @@ int nfs_write_inode(struct inode *inode,
{
int ret;
- if (sync) {
- ret = filemap_fdatawait(inode->i_mapping);
- if (ret == 0)
- ret = nfs_commit_inode(inode, FLUSH_SYNC);
- } else
- ret = nfs_commit_inode(inode, 0);
+ ret = nfs_commit_inode(inode, sync ? FLUSH_SYNC : 0);
if (ret >= 0)
return 0;
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
Index: linux-2.6/fs/xfs/linux-2.6/xfs_super.c
===================================================================
--- linux-2.6.orig/fs/xfs/linux-2.6/xfs_super.c 2010-01-11 15:55:16.917003903 +0100
+++ linux-2.6/fs/xfs/linux-2.6/xfs_super.c 2010-01-11 15:55:24.764006427 +0100
@@ -1044,12 +1044,6 @@ xfs_fs_write_inode(
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
- if (sync) {
- error = xfs_wait_on_pages(ip, 0, -1);
- if (error)
- goto out;
- }
-
/*
* Bypass inodes which have already been cleaned by
* the inode flush clustering code inside xfs_iflush
--
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
