From patchwork Wed Jul 25 08:47:01 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Max Gurtovoy X-Patchwork-Id: 10543707 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 68D6217FD for ; Wed, 25 Jul 2018 08:47:09 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 4C33B29B8D for ; Wed, 25 Jul 2018 08:47:09 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 40E8C29B8F; Wed, 25 Jul 2018 08:47:09 +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=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI,UNPARSEABLE_RELAY 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 A988A29B8B for ; Wed, 25 Jul 2018 08:47:08 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728619AbeGYJ5s (ORCPT ); Wed, 25 Jul 2018 05:57:48 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:34264 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728385AbeGYJ5s (ORCPT ); Wed, 25 Jul 2018 05:57:48 -0400 Received: from Internal Mail-Server by MTLPINE1 (envelope-from maxg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 25 Jul 2018 11:50:18 +0300 Received: from r-vnc08.mtr.labs.mlnx (r-vnc08.mtr.labs.mlnx [10.208.0.121]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id w6P8l2PG025016; Wed, 25 Jul 2018 11:47:02 +0300 From: Max Gurtovoy To: keith.busch@intel.com, linux-nvme@lists.infradead.org, sagi@grimberg.me, hch@lst.de, martin.petersen@oracle.com, linux-block@vger.kernel.org, axboe@kernel.dk Cc: vladimirk@mellanox.com, Max Gurtovoy Subject: [PATCH v3 3/3] nvme: use blk API to remap ref tags for IOs with metadata Date: Wed, 25 Jul 2018 11:47:01 +0300 Message-Id: <1532508421-2711-3-git-send-email-maxg@mellanox.com> X-Mailer: git-send-email 1.7.8.2 In-Reply-To: <1532508421-2711-1-git-send-email-maxg@mellanox.com> References: <1532508421-2711-1-git-send-email-maxg@mellanox.com> 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 Also moved the logic of the remapping to the nvme core driver instead of implementing it in the nvme pci driver. This way all the other nvme transport drivers will benefit from it (in case they'll implement metadata support). Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Cc: Jens Axboe Cc: Martin K. Petersen Signed-off-by: Max Gurtovoy --- changes from v2: - add Reviewed-by tag changes from v1: - check status of nvme_req instead of converting to BLK_STS --- drivers/nvme/host/core.c | 18 ++++++++++++ drivers/nvme/host/nvme.h | 9 +----- drivers/nvme/host/pci.c | 75 +----------------------------------------------- 3 files changed, 20 insertions(+), 82 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 191177b..b57abe5 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -617,6 +617,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, if (WARN_ON_ONCE(!nvme_ns_has_pi(ns))) return BLK_STS_NOTSUPP; control |= NVME_RW_PRINFO_PRACT; + } else if (req_op(req) == REQ_OP_WRITE) { + t10_pi_prepare(req, ns->pi_type); } switch (ns->pi_type) { @@ -637,6 +639,22 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, return 0; } +void nvme_cleanup_cmd(struct request *req) +{ + if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && + nvme_req(req)->status == 0) { + struct nvme_ns *ns = req->rq_disk->private_data; + + t10_pi_complete(req, ns->pi_type, + blk_rq_bytes(req) >> ns->lba_shift); + } + if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { + kfree(page_address(req->special_vec.bv_page) + + req->special_vec.bv_offset); + } +} +EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); + blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, struct nvme_command *cmd) { diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 0c4a33d..dfc01ff 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -356,14 +356,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) return (sector >> (ns->lba_shift - 9)); } -static inline void nvme_cleanup_cmd(struct request *req) -{ - if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { - kfree(page_address(req->special_vec.bv_page) + - req->special_vec.bv_offset); - } -} - static inline void nvme_end_request(struct request *req, __le16 status, union nvme_result result) { @@ -420,6 +412,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, #define NVME_QID_ANY -1 struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid); +void nvme_cleanup_cmd(struct request *req); blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, struct nvme_command *cmd); int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ddd441b..03beac5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -535,73 +535,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req) mempool_free(iod->sg, dev->iod_mempool); } -#ifdef CONFIG_BLK_DEV_INTEGRITY -static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi) -{ - if (be32_to_cpu(pi->ref_tag) == v) - pi->ref_tag = cpu_to_be32(p); -} - -static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) -{ - if (be32_to_cpu(pi->ref_tag) == p) - pi->ref_tag = cpu_to_be32(v); -} - -/** - * nvme_dif_remap - remaps ref tags to bip seed and physical lba - * - * The virtual start sector is the one that was originally submitted by the - * block layer. Due to partitioning, MD/DM cloning, etc. the actual physical - * start sector may be different. Remap protection information to match the - * physical LBA on writes, and back to the original seed on reads. - * - * Type 0 and 3 do not have a ref tag, so no remapping required. - */ -static void nvme_dif_remap(struct request *req, - void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi)) -{ - struct nvme_ns *ns = req->rq_disk->private_data; - struct bio_integrity_payload *bip; - struct t10_pi_tuple *pi; - void *p, *pmap; - u32 i, nlb, ts, phys, virt; - - if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3) - return; - - bip = bio_integrity(req->bio); - if (!bip) - return; - - pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset; - - p = pmap; - virt = bip_get_seed(bip); - phys = nvme_block_nr(ns, blk_rq_pos(req)); - nlb = (blk_rq_bytes(req) >> ns->lba_shift); - ts = ns->disk->queue->integrity.tuple_size; - - for (i = 0; i < nlb; i++, virt++, phys++) { - pi = (struct t10_pi_tuple *)p; - dif_swap(phys, virt, pi); - p += ts; - } - kunmap_atomic(pmap); -} -#else /* CONFIG_BLK_DEV_INTEGRITY */ -static void nvme_dif_remap(struct request *req, - void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi)) -{ -} -static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi) -{ -} -static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) -{ -} -#endif - static void nvme_print_sgl(struct scatterlist *sgl, int nents) { int i; @@ -827,9 +760,6 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1) goto out_unmap; - if (req_op(req) == REQ_OP_WRITE) - nvme_dif_remap(req, nvme_dif_prep); - if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir)) goto out_unmap; } @@ -852,11 +782,8 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) if (iod->nents) { dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir); - if (blk_integrity_rq(req)) { - if (req_op(req) == REQ_OP_READ) - nvme_dif_remap(req, nvme_dif_complete); + if (blk_integrity_rq(req)) dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir); - } } nvme_cleanup_cmd(req);