Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753988AbbG0JmD (ORCPT ); Mon, 27 Jul 2015 05:42:03 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:36580 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752498AbbG0JmA (ORCPT ); Mon, 27 Jul 2015 05:42:00 -0400 MIME-Version: 1.0 In-Reply-To: <20150727084020.GA28336@infradead.org> References: <1437061068-26118-1-git-send-email-ming.lei@canonical.com> <1437061068-26118-5-git-send-email-ming.lei@canonical.com> <20150727084020.GA28336@infradead.org> Date: Mon, 27 Jul 2015 05:41:57 -0400 Message-ID: Subject: Re: [PATCH v7 4/6] block: loop: prepare for supporing direct IO From: Ming Lei To: Christoph Hellwig Cc: Jens Axboe , Linux Kernel Mailing List , "Justin M. Forbes" , Jeff Moyer , Tejun Heo , linux-api@vger.kernel.org Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1512 Lines: 42 On Mon, Jul 27, 2015 at 4:40 AM, Christoph Hellwig wrote: >> + /* >> + * loop block's logical block size is 512, now >> + * we support direct I/O only if the backing >> + * block devices' minimize I/O size is 512 and >> + * the offset is aligned with 512. >> + */ >> + if (dio) { >> + if (inode->i_sb->s_bdev && >> + bdev_io_min(inode->i_sb->s_bdev) == 512 && >> + !(lo->lo_offset & 511)) > > Why the hardcoded value? I suspect this should be more like: > > if (dio && inode->i_sb->s_bdev && > (lo->lo_offset & (bdev_io_min(inode->i_sb->s_bdev) - 1)) != 0) > dio = false; The above can't work if the backing device has a bigger sector size (such as 4K), that is why loop's direct-io requires 512 min_io_size of backing device. > >> + blk_mq_freeze_queue(lo->lo_queue); >> + lo->use_dio = use_dio; >> + if (use_dio) >> + lo->lo_flags |= LO_FLAGS_DIRECT_IO; >> + else >> + lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; >> + blk_mq_unfreeze_queue(lo->lo_queue); > > Locking? __loop_update_dio() is only called inside ioctl path, so mutex of lo->lo_ctl_mutex has been held already. Thanks, -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/