From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934009AbcCHAFS (ORCPT ); Mon, 7 Mar 2016 19:05:18 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:45059 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933989AbcCHAEj (ORCPT ); Mon, 7 Mar 2016 19:04:39 -0500 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Sagi Grimberg , Christoph Hellwig , Ming Lei , Jens Axboe Subject: [PATCH 4.4 69/74] block: check virt boundary in bio_will_gap() Date: Mon, 7 Mar 2016 16:03:34 -0800 Message-Id: <20160308000317.486365050@linuxfoundation.org> X-Mailer: git-send-email 2.7.2 In-Reply-To: <20160308000315.294406921@linuxfoundation.org> References: <20160308000315.294406921@linuxfoundation.org> User-Agent: quilt/0.64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Ming Lei commit e0af29171aa8912e1ca95023b75ef336cd70d661 upstream. In the following patch, the way for figuring out the last bvec will be changed with a bit cost introduced, so return immediately if the queue doesn't have virt boundary limit. Actually most of devices have not this limit. Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/blkdev.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1367,6 +1367,13 @@ static inline void put_dev_sector(Sector page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. @@ -1376,18 +1383,17 @@ static inline bool bvec_gap_to_prev(stru { if (!queue_virt_boundary(q)) return false; - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return __bvec_gap_to_prev(q, bprv, offset); } static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev)) + if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; - return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], + next->bi_io_vec[0].bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio)