diff options
| author | Steve French <stfrench@microsoft.com> | 2021-03-26 18:41:55 -0500 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2021-03-30 14:32:07 +0200 |
| commit | 86cc799e1d9d96358ed8fe4c868b42b2fd6c7646 (patch) | |
| tree | ae4548a3cdbbc2a7ae724b1d3ba765142f06812d /sound/aoa/core/gpio-feature.c | |
| parent | 2423511cc5baf23bdac3dbc171beab094c3b5107 (diff) | |
| download | linux-stable-86cc799e1d9d96358ed8fe4c868b42b2fd6c7646.tar.gz linux-stable-86cc799e1d9d96358ed8fe4c868b42b2fd6c7646.tar.bz2 linux-stable-86cc799e1d9d96358ed8fe4c868b42b2fd6c7646.zip | |
smb3: fix cached file size problems in duplicate extents (reflink)
commit cfc63fc8126a93cbf95379bc4cad79a7b15b6ece upstream.
There were two problems (one of which could cause data corruption)
that were noticed with duplicate extents (ie reflink)
when debugging why various xfstests were being incorrectly skipped
(e.g. generic/138, generic/140, generic/142). First, we were not
updating the file size locally in the cache when extending a
file due to reflink (it would refresh after actimeo expires)
but xfstest was checking the size immediately which was still
0 so caused the test to be skipped. Second, we were setting
the target file size (which could shrink the file) in all cases
to the end of the reflinked range rather than only setting the
target file size when reflink would extend the file.
CC: <stable@vger.kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'sound/aoa/core/gpio-feature.c')
0 files changed, 0 insertions, 0 deletions