[XFS] Fix race in xfs_write() between direct and buffered I/O with DMAPI
The iolock is dropped and re-acquired around the call to XFS_SEND_NAMESP().
While the iolock is released the file can become cached. We then
'goto retry' and - if we are doing direct I/O - mapping->nrpages may now be
non zero but need_i_mutex will be zero and we will hit the WARN_ON().
Since we have dropped the I/O lock then the file size may have also changed
so what we need to do here is 'goto start' like we do for the XFS_SEND_DATA()
DMAPI event.
We also need to update the filesize before releasing the iolock so that
needs to be done before the XFS_SEND_NAMESP event. If we drop the iolock
before setting the filesize we could race with a truncate.
Reviewed-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 92ce34b..7e90daa 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -707,7 +707,6 @@
}
}
-retry:
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
@@ -763,6 +762,17 @@
if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
ret = wait_on_sync_kiocb(iocb);
+ isize = i_size_read(inode);
+ if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
+ *offset = isize;
+
+ if (*offset > xip->i_size) {
+ xfs_ilock(xip, XFS_ILOCK_EXCL);
+ if (*offset > xip->i_size)
+ xip->i_size = *offset;
+ xfs_iunlock(xip, XFS_ILOCK_EXCL);
+ }
+
if (ret == -ENOSPC &&
DM_EVENT_ENABLED(xip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
xfs_iunlock(xip, iolock);
@@ -776,20 +786,7 @@
xfs_ilock(xip, iolock);
if (error)
goto out_unlock_internal;
- pos = xip->i_size;
- ret = 0;
- goto retry;
- }
-
- isize = i_size_read(inode);
- if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
- *offset = isize;
-
- if (*offset > xip->i_size) {
- xfs_ilock(xip, XFS_ILOCK_EXCL);
- if (*offset > xip->i_size)
- xip->i_size = *offset;
- xfs_iunlock(xip, XFS_ILOCK_EXCL);
+ goto start;
}
error = -ret;