J. Bruce Fields 60017643c2 NFS: commit direct writes even if they fail partially
commit 1b8d97b0a837beaf48a8449955b52c650a7114b4 upstream.

If some of the WRITE calls making up an O_DIRECT write syscall fail,
we neglect to commit, even if some of the WRITEs succeed.

We also depend on the commit code to free the reference count on the
nfs_page taken in the "if (request_commit)" case at the end of
nfs_direct_write_completion().  The problem was originally noticed
because ENOSPC's encountered partway through a write would result in a
closed file being sillyrenamed when it should have been unlinked.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-16 20:22:58 +01:00
..
2017-12-14 09:53:15 +01:00
2017-08-24 13:23:03 -07:00
2017-12-14 09:53:14 +01:00
2017-11-30 08:40:45 +00:00
2017-09-04 19:05:15 -04:00
2017-11-30 08:40:53 +00:00
2017-10-18 14:51:50 -04:00
2018-01-05 15:48:57 +01:00
2018-02-03 17:38:53 +01:00