From patchwork Mon Jun 19 16:33:45 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Goldwyn Rodrigues X-Patchwork-Id: 9796785 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 9E5CA60381 for ; Mon, 19 Jun 2017 16:34:12 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 887CC26E69 for ; Mon, 19 Jun 2017 16:34:12 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 7B45726E56; Mon, 19 Jun 2017 16:34:12 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id CB1D626E56 for ; Mon, 19 Jun 2017 16:34:11 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751098AbdFSQeL (ORCPT ); Mon, 19 Jun 2017 12:34:11 -0400 Received: from mx2.suse.de ([195.135.220.15]:54391 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751071AbdFSQeK (ORCPT ); Mon, 19 Jun 2017 12:34:10 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (charybdis-ext.suse.de [195.135.220.254]) by mx1.suse.de (Postfix) with ESMTP id 719C8AD09; Mon, 19 Jun 2017 16:34:09 +0000 (UTC) From: Goldwyn Rodrigues To: axboe@kernel.dk Cc: viro@ZenIV.linux.org.uk, hch@lst.de, jack@suse.cz, akpm@linux-foundation.org, linux-block@vger.kernel.org, Goldwyn Rodrigues Subject: [PATCH 07/10] block: return on congested block device Date: Mon, 19 Jun 2017 11:33:45 -0500 Message-Id: <20170619163348.15542-8-rgoldwyn@suse.de> X-Mailer: git-send-email 2.12.0 In-Reply-To: <20170619163348.15542-1-rgoldwyn@suse.de> References: <20170619163348.15542-1-rgoldwyn@suse.de> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Goldwyn Rodrigues A new bio operation flag REQ_NOWAIT is introduced to identify bio's orignating from iocb with IOCB_NOWAIT. This flag indicates to return immediately if a request cannot be made instead of retrying. Stacked devices such as md (the ones with make_request_fn hooks) currently are not supported because it may block for housekeeping. For example, an md can have a part of the device suspended. For this reason, only request based devices are supported. In the future, this feature will be expanded to stacked devices by teaching them how to handle the REQ_NOWAIT flags. Reviewed-by: Christoph Hellwig Reviewed-by: Jens Axboe Signed-off-by: Goldwyn Rodrigues --- block/blk-core.c | 22 ++++++++++++++++++++-- block/blk-mq-sched.c | 3 +++ block/blk-mq.c | 2 ++ fs/direct-io.c | 10 ++++++++-- include/linux/bio.h | 6 ++++++ include/linux/blk_types.h | 4 ++++ 6 files changed, 43 insertions(+), 4 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 8592409db272..3999e6ac288d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -143,6 +143,7 @@ static const struct { [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, + [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, @@ -1314,6 +1315,11 @@ static struct request *get_request(struct request_queue *q, unsigned int op, if (!IS_ERR(rq)) return rq; + if (op & REQ_NOWAIT) { + blk_put_rl(rl); + return ERR_PTR(-EAGAIN); + } + if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) { blk_put_rl(rl); return rq; @@ -1961,6 +1967,14 @@ generic_make_request_checks(struct bio *bio) goto end_io; } + /* + * For a REQ_NOWAIT based request, return -EOPNOTSUPP + * if queue is not a request based queue. + */ + + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q)) + goto not_supported; + part = bio->bi_bdev->bd_part; if (should_fail_request(part, bio->bi_iter.bi_size) || should_fail_request(&part_to_disk(part)->part0, @@ -2118,7 +2132,7 @@ blk_qc_t generic_make_request(struct bio *bio) do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - if (likely(blk_queue_enter(q, false) == 0)) { + if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) { struct bio_list lower, same; /* Create a fresh bio_list for all subordinate requests */ @@ -2143,7 +2157,11 @@ blk_qc_t generic_make_request(struct bio *bio) bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } else { - bio_io_error(bio); + if (unlikely(!blk_queue_dying(q) && + (bio->bi_opf & REQ_NOWAIT))) + bio_wouldblock_error(bio); + else + bio_io_error(bio); } bio = bio_list_pop(&bio_list_on_stack[0]); } while (bio); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index c4e2afb9d12d..ab14295d8468 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -83,6 +83,9 @@ struct request *blk_mq_sched_get_request(struct request_queue *q, if (likely(!data->hctx)) data->hctx = blk_mq_map_queue(q, data->ctx->cpu); + if (op & REQ_NOWAIT) + data->flags |= BLK_MQ_REQ_NOWAIT; + if (e) { data->flags |= BLK_MQ_REQ_INTERNAL; diff --git a/block/blk-mq.c b/block/blk-mq.c index 359d2dc0d414..387fc8e8a2ba 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1498,6 +1498,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data); if (unlikely(!rq)) { __wbt_done(q->rq_wb, wb_acct); + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); return BLK_QC_T_NONE; } diff --git a/fs/direct-io.c b/fs/direct-io.c index e8baaabebf13..c87077d1dc33 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -479,8 +479,12 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) unsigned i; blk_status_t err = bio->bi_status; - if (err) - dio->io_error = -EIO; + if (err) { + if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT)) + dio->io_error = -EAGAIN; + else + dio->io_error = -EIO; + } if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) { bio_check_pages_dirty(bio); /* transfers ownership */ @@ -1194,6 +1198,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, if (iov_iter_rw(iter) == WRITE) { dio->op = REQ_OP_WRITE; dio->op_flags = REQ_SYNC | REQ_IDLE; + if (iocb->ki_flags & IOCB_NOWAIT) + dio->op_flags |= REQ_NOWAIT; } else { dio->op = REQ_OP_READ; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 9455aada1399..1eb47e8c6965 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -418,6 +418,12 @@ static inline void bio_io_error(struct bio *bio) bio_endio(bio); } +static inline void bio_wouldblock_error(struct bio *bio) +{ + bio->bi_status = BLK_STS_AGAIN; + bio_endio(bio); +} + struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dcd45b15a3a5..e210da6d14b8 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -36,6 +36,8 @@ typedef u8 __bitwise blk_status_t; /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) +#define BLK_STS_AGAIN ((__force blk_status_t)12) + struct blk_issue_stat { u64 stat; }; @@ -224,6 +226,7 @@ enum req_flag_bits { /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ + __REQ_NOWAIT, /* Don't wait if request will block */ __REQ_NR_BITS, /* stops here */ }; @@ -242,6 +245,7 @@ enum req_flag_bits { #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) +#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)