From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: [PATCH 3/3] ext4: pass in DIO_SKIP_DIO_COUNT to do_blockdev_direct_IO() Date: Wed, 15 Apr 2015 16:01:38 -0600 Message-ID: <1429135298-17153-4-git-send-email-axboe@fb.com> References: <1429135298-17153-1-git-send-email-axboe@fb.com> Mime-Version: 1.0 Content-Type: text/plain Cc: Jens Axboe , "Theodore Ts'o" To: , Return-path: Received: from mx0b-00082601.pphosted.com ([67.231.153.30]:10858 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755719AbbDOWBr (ORCPT ); Wed, 15 Apr 2015 18:01:47 -0400 In-Reply-To: <1429135298-17153-1-git-send-email-axboe@fb.com> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: For writes, ext4_ext_direct_IO() already holds the inode i_dio_count elevated, so we don't need the extra inc/dec that is done in do_blockdev_direct_IO(). Pass in DIO_SKIP_DIO_COUNT to tell it that. Cc: Theodore Ts'o Signed-off-by: Jens Axboe --- fs/ext4/inode.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 62d4615aa9b0..2605355791a3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2977,8 +2977,10 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * conversion. This also disallows race between truncate() and * overwrite DIO as i_dio_count needs to be incremented under i_mutex. */ - if (rw == WRITE) + if (rw == WRITE) { inode_dio_inc(inode); + dio_flags |= DIO_SKIP_DIO_COUNT; + } /* If we do a overwrite dio, i_mutex locking can be released */ overwrite = *((int *)iocb->private); @@ -3032,7 +3034,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, get_block_func = ext4_get_block_write_nolock; } else { get_block_func = ext4_get_block_write; - dio_flags = DIO_LOCKING; + dio_flags |= DIO_LOCKING; } if (IS_DAX(inode)) ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func, -- 1.9.1