From patchwork Tue Sep 27 01:44:19 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 12989655 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 97D9FC6FA92 for ; Tue, 27 Sep 2022 01:44:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229948AbiI0Boe (ORCPT ); Mon, 26 Sep 2022 21:44:34 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56800 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229966AbiI0Boa (ORCPT ); Mon, 26 Sep 2022 21:44:30 -0400 Received: from mail-pg1-x531.google.com (mail-pg1-x531.google.com [IPv6:2607:f8b0:4864:20::531]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 15A93A74D6 for ; Mon, 26 Sep 2022 18:44:28 -0700 (PDT) Received: by mail-pg1-x531.google.com with SMTP id u69so8124612pgd.2 for ; Mon, 26 Sep 2022 18:44:27 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date; bh=OWQyl94A5qNKtPnF/8PyOhg9aeGApg21Zf8bAO/j86s=; b=mP3PeN6PCELyvJQ+DXmQS2FoJwddmxuB7MQ2/UGEabb+Nm+/V452tOJaIqhRCFbWIv IDC2qnSZZmCGdo5dh/q1ZBrd1oigApYXtLJPSyGuJcrx8rVIz3Xa9fMTdc/32SjSGYm7 R1IZP4E6Ph619vy2hU2ZZMhbef7T8doLfRUOMdOWG67R4osTEnmvvI4sEeF4Dotkbtmv CrJeo7+GHMCQX9bmnTYIvdrUCh1UfScfimPbsJ1bRgeXH5KLwHYydc/+NxR7gHcVuM7W vDmc3SweNBhuBsmVtob4aqGhkqVJzVipuHgB1xuPXoC3Yk7y4SIW9wNbXnUChX9C0mQN sIpw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date; bh=OWQyl94A5qNKtPnF/8PyOhg9aeGApg21Zf8bAO/j86s=; b=bMG/S6P7pF04XeYw94gxNp8Kjl2z2tdq1dVGugjkzEgkS7tmFu5la0RqGrTYhHcNuu YR2BMUrHjzU+nd9vBFeC6PmY7OPLSDyC8udbYgfB55cE3ebHRnHdIxVj5bBBp+N6dG/A X9WXqSk8xzfuAVHXIkul4bA1FGwA0PE0SRv0FVN9bm1fIKKxo9OaESPGUc5RJfP4nvPP +TQ9by9I7XLtZ7FfxGUc65KFGgSheCV5OhnTNj52o57TquyyD5j2A+Ua9S9QlIBblzQo m6b2KAeG0u3n/jS3Tt+Smb68Br1cENEXjYsiB4TTasz+ieBVjIg6PTz2MAvPDxZ8F6Hv mJtw== X-Gm-Message-State: ACrzQf0p7XuCG/29AgAvAtlZRUfYiReMP0Piqq+CBNXB0GajN672tEbn SpfjMKHjLj69z7hF5tBFa8WtK1YBirMkgg== X-Google-Smtp-Source: AMsMyM4b4xjI5VuwTPQxKRtlKpdTkx4cE0vHyJY+Uc0NtDg0sPzbmbmbPkA9/NgxXSIQ4gKYg+MuEw== X-Received: by 2002:a62:1bc8:0:b0:546:c62e:e84 with SMTP id b191-20020a621bc8000000b00546c62e0e84mr26532012pfb.45.1664243066985; Mon, 26 Sep 2022 18:44:26 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id o2-20020aa79782000000b00537d60286c9sm183062pfp.113.2022.09.26.18.44.26 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Sep 2022 18:44:26 -0700 (PDT) From: Jens Axboe To: linux-block@vger.kernel.org Cc: linux-scsi@vger.kernel.org, linux-nvme@lists.infradead.org, Jens Axboe , Stefan Roesch Subject: [PATCH 4/5] nvme: split out metadata vs non metadata end_io uring_cmd completions Date: Mon, 26 Sep 2022 19:44:19 -0600 Message-Id: <20220927014420.71141-5-axboe@kernel.dk> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20220927014420.71141-1-axboe@kernel.dk> References: <20220927014420.71141-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org By splitting up the metadata and non-metadata end_io handling, we can remove any request dependencies on the normal non-metadata IO path. This is in preparation for enabling the normal IO passthrough path to pass the ownership of the request back to the block layer. Co-developed-by: Stefan Roesch Signed-off-by: Jens Axboe Reviewed-by: Christoph Hellwig Reviewed-by: Anuj Gupta Reviewed-by: Sagi Grimberg --- drivers/nvme/host/ioctl.c | 79 ++++++++++++++++++++++++++++++--------- 1 file changed, 61 insertions(+), 18 deletions(-) diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index c80b3ecca5c8..9e356a6c96c2 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -349,9 +349,15 @@ struct nvme_uring_cmd_pdu { struct bio *bio; struct request *req; }; - void *meta; /* kernel-resident buffer */ - void __user *meta_buffer; u32 meta_len; + u32 nvme_status; + union { + struct { + void *meta; /* kernel-resident buffer */ + void __user *meta_buffer; + }; + u64 result; + } u; }; static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( @@ -360,11 +366,10 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; } -static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); struct request *req = pdu->req; - struct bio *bio = req->bio; int status; u64 result; @@ -375,27 +380,39 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) result = le64_to_cpu(nvme_req(req)->result.u64); - if (pdu->meta) - status = nvme_finish_user_metadata(req, pdu->meta_buffer, - pdu->meta, pdu->meta_len, status); - if (bio) - blk_rq_unmap_user(bio); + if (pdu->meta_len) + status = nvme_finish_user_metadata(req, pdu->u.meta_buffer, + pdu->u.meta, pdu->meta_len, status); + if (req->bio) + blk_rq_unmap_user(req->bio); blk_mq_free_request(req); io_uring_cmd_done(ioucmd, status, result); } +static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +{ + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + + if (pdu->bio) + blk_rq_unmap_user(pdu->bio); + + io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result); +} + static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, blk_status_t err) { struct io_uring_cmd *ioucmd = req->end_io_data; struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - /* extract bio before reusing the same field for request */ - struct bio *bio = pdu->bio; void *cookie = READ_ONCE(ioucmd->cookie); - pdu->req = req; - req->bio = bio; + req->bio = pdu->bio; + if (nvme_req(req)->flags & NVME_REQ_CANCELLED) + pdu->nvme_status = -EINTR; + else + pdu->nvme_status = nvme_req(req)->status; + pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64); /* * For iopoll, complete it directly. @@ -406,6 +423,29 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); + blk_mq_free_request(req); + return RQ_END_IO_NONE; +} + +static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, + blk_status_t err) +{ + struct io_uring_cmd *ioucmd = req->end_io_data; + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + void *cookie = READ_ONCE(ioucmd->cookie); + + req->bio = pdu->bio; + pdu->req = req; + + /* + * For iopoll, complete it directly. + * Otherwise, move the completion to task work. + */ + if (cookie != NULL && blk_rq_is_poll(req)) + nvme_uring_task_meta_cb(ioucmd); + else + io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_meta_cb); + return RQ_END_IO_NONE; } @@ -467,8 +507,6 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, blk_flags); if (IS_ERR(req)) return PTR_ERR(req); - req->end_io = nvme_uring_cmd_end_io; - req->end_io_data = ioucmd; if (issue_flags & IO_URING_F_IOPOLL && rq_flags & REQ_POLLED) { if (unlikely(!req->bio)) { @@ -483,10 +521,15 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, } /* to free bio on completion, as req->bio will be null at that time */ pdu->bio = req->bio; - pdu->meta = meta; - pdu->meta_buffer = nvme_to_user_ptr(d.metadata); pdu->meta_len = d.metadata_len; - + req->end_io_data = ioucmd; + if (pdu->meta_len) { + pdu->u.meta = meta; + pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata); + req->end_io = nvme_uring_cmd_end_io_meta; + } else { + req->end_io = nvme_uring_cmd_end_io; + } blk_execute_rq_nowait(req, false); return -EIOCBQUEUED; }