Commit ab0a9735e06914ce4d2a94ffa41497dbc142fe7f

Authored by Christoph Hellwig
Committed by Jens Axboe
1 parent b9d128f108

blkdev: flush disk cache on ->fsync

Currently there is no barrier support in the block device code.  That
means we cannot guarantee any sort of data integerity when using the
block device node with dis kwrite caches enabled.  Using the raw block
device node is a typical use case for virtualization (and I assume
databases, too).  This patch changes block_fsync to issue a cache flush
and thus make fsync on block device nodes actually useful.

Note that in mainline we would also need to add such code to the
->aio_write method for O_SYNC handling, but assuming that Jan's patch
series for the O_SYNC rewrite goes in it will also call into ->fsync
for 2.6.32.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

Showing 1 changed file with 11 additions and 1 deletions Side-by-side Diff

... ... @@ -405,7 +405,17 @@
405 405  
406 406 static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
407 407 {
408   - return sync_blockdev(I_BDEV(filp->f_mapping->host));
  408 + struct block_device *bdev = I_BDEV(filp->f_mapping->host);
  409 + int error;
  410 +
  411 + error = sync_blockdev(bdev);
  412 + if (error)
  413 + return error;
  414 +
  415 + error = blkdev_issue_flush(bdev, NULL);
  416 + if (error == -EOPNOTSUPP)
  417 + error = 0;
  418 + return error;
409 419 }
410 420  
411 421 /*