Path: csiph.com!1.us.feeder.erje.net!2.us.feeder.erje.net!feeder.erje.net!1.eu.feeder.erje.net!weretis.net!feeder4.news.weretis.net!news.unit0.net!news.panservice.it!bofh.it!news.nic.it!robomod From: Greg Kroah-Hartman Newsgroups: linux.kernel Subject: [PATCH 4.10 05/81] xfs: fix eofblocks race with file extending async dio writes Date: Thu, 06 Apr 2017 11:10:04 +0200 Message-ID: References: X-Mailer: git-send-email 2.12.2 User-Agent: quilt/0.65 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: robomod@news.nic.it List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Approved: robomod@news.nic.it Lines: 60 Organization: linux.* mail to news gateway X-Original-Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Brian Foster , Christoph Hellwig , "Darrick J. Wong" X-Original-Date: Thu, 6 Apr 2017 10:37:57 +0200 X-Original-Message-ID: <20170406083624.540296921@linuxfoundation.org> X-Original-References: <20170406083624.322941631@linuxfoundation.org> X-Original-Sender: linux-kernel-owner@vger.kernel.org Xref: csiph.com linux.kernel:1617707 4.10-stable review patch. If anyone has any objections, please let me know. ------------------ From: Brian Foster commit e4229d6b0bc9280f29624faf170cf76a9f1ca60e upstream. It's possible for post-eof blocks to end up being used for direct I/O writes. dio write performs an upfront unwritten extent allocation, sends the dio and then updates the inode size (if necessary) on write completion. If a file release occurs while a file extending dio write is in flight, it is possible to mistake the post-eof blocks for speculative preallocation and incorrectly truncate them from the inode. This means that the resulting dio write completion can discover a hole and allocate new blocks rather than perform unwritten extent conversion. This requires a strange mix of I/O and is thus not likely to reproduce in real world workloads. It is intermittently reproduced by generic/299. The error manifests as an assert failure due to transaction overrun because the aforementioned write completion transaction has only reserved enough blocks for btree operations: XFS: Assertion failed: tp->t_blk_res_used <= tp->t_blk_res, \ file: fs/xfs//xfs_trans.c, line: 309 The root cause is that xfs_free_eofblocks() uses i_size to truncate post-eof blocks from the inode, but async, file extending direct writes do not update i_size until write completion, long after inode locks are dropped. Therefore, xfs_free_eofblocks() effectively truncates the inode to the incorrect size. Update xfs_free_eofblocks() to serialize against dio similar to how extending writes are serialized against i_size updates before post-eof block zeroing. Specifically, wait on dio while under the iolock. This ensures that dio write completions have updated i_size before post-eof blocks are processed. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_bmap_util.c | 3 +++ 1 file changed, 3 insertions(+) --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -959,6 +959,9 @@ xfs_free_eofblocks( if (error) return error; + /* wait on dio to ensure i_size has settled */ + inode_dio_wait(VFS_I(ip)); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) {