From patchwork Fri Jun 17 10:55:17 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: John Garry X-Patchwork-Id: 12885568 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 46425C43334 for ; Fri, 17 Jun 2022 11:01:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1382272AbiFQLBz (ORCPT ); Fri, 17 Jun 2022 07:01:55 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56694 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1381563AbiFQLBq (ORCPT ); Fri, 17 Jun 2022 07:01:46 -0400 Received: from frasgout.his.huawei.com (frasgout.his.huawei.com [185.176.79.56]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 369F36C0CF; Fri, 17 Jun 2022 04:01:45 -0700 (PDT) Received: from fraeml710-chm.china.huawei.com (unknown [172.18.147.206]) by frasgout.his.huawei.com (SkyGuard) with ESMTP id 4LPbhC6ZMMz689NN; Fri, 17 Jun 2022 19:01:31 +0800 (CST) Received: from lhreml724-chm.china.huawei.com (10.201.108.75) by fraeml710-chm.china.huawei.com (10.206.15.59) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.24; Fri, 17 Jun 2022 13:01:43 +0200 Received: from localhost.localdomain (10.69.192.58) by lhreml724-chm.china.huawei.com (10.201.108.75) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.24; Fri, 17 Jun 2022 12:01:38 +0100 From: John Garry To: , , , , , , , , , CC: , , , , , , , , , John Garry Subject: [PATCH 2/5] blk-mq: Add a flag for reserved requests Date: Fri, 17 Jun 2022 18:55:17 +0800 Message-ID: <1655463320-241202-3-git-send-email-john.garry@huawei.com> X-Mailer: git-send-email 2.8.1 In-Reply-To: <1655463320-241202-1-git-send-email-john.garry@huawei.com> References: <1655463320-241202-1-git-send-email-john.garry@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.69.192.58] X-ClientProxiedBy: dggems706-chm.china.huawei.com (10.3.19.183) To lhreml724-chm.china.huawei.com (10.201.108.75) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org Add a flag for reserved requests so that drivers may know this for any special handling. Signed-off-by: John Garry Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke --- block/blk-mq.c | 6 ++++++ include/linux/blk-mq.h | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/block/blk-mq.c b/block/blk-mq.c index 7a5558bbc7f6..15e66416de60 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -474,6 +474,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) if (!(data->rq_flags & RQF_ELV)) blk_mq_tag_busy(data->hctx); + if (data->flags & BLK_MQ_REQ_RESERVED) + data->rq_flags |= RQF_RESV; + /* * Try batched alloc if we want more than 1 tag. */ @@ -586,6 +589,9 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, else data.rq_flags |= RQF_ELV; + if (flags & BLK_MQ_REQ_RESERVED) + data.rq_flags |= RQF_RESV; + ret = -EWOULDBLOCK; tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e2d9daf7e8dd..6d81fe10e850 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -57,6 +57,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* queue has elevator attached */ #define RQF_ELV ((__force req_flags_t)(1 << 22)) +#define RQF_RESV ((__force req_flags_t)(1 << 23)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ @@ -823,6 +824,11 @@ static inline bool blk_mq_need_time_stamp(struct request *rq) return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); } +static inline bool blk_mq_is_reserved_rq(struct request *rq) +{ + return rq->rq_flags & RQF_RESV; +} + /* * Batched completions only work when there is no I/O error and no special * ->end_io handler.