From patchwork Wed Aug 2 18:41:19 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dave Jiang X-Patchwork-Id: 9877411 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 C948C602BC for ; Wed, 2 Aug 2017 18:41:25 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id B0EA728832 for ; Wed, 2 Aug 2017 18:41:25 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id A5A9A2881E; Wed, 2 Aug 2017 18:41:25 +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=unavailable 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 4DE132881E for ; Wed, 2 Aug 2017 18:41:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752461AbdHBSlX (ORCPT ); Wed, 2 Aug 2017 14:41:23 -0400 Received: from mga02.intel.com ([134.134.136.20]:30620 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752456AbdHBSlX (ORCPT ); Wed, 2 Aug 2017 14:41:23 -0400 Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga101.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 02 Aug 2017 11:41:22 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.41,312,1498546800"; d="scan'208";a="118812668" Received: from djiang5-desk3.ch.intel.com ([143.182.137.38]) by orsmga002.jf.intel.com with ESMTP; 02 Aug 2017 11:41:19 -0700 Subject: [PATCH v2 4/5] libnvdimm: Adding blk-mq support to the pmem driver From: Dave Jiang To: vinod.koul@intel.com, dan.j.williams@intel.com Cc: dmaengine@vger.kernel.org, ross.zwisler@linux.intel.com, linux-nvdimm@lists.01.org Date: Wed, 02 Aug 2017 11:41:19 -0700 Message-ID: <150169927933.59677.7382159914302175097.stgit@djiang5-desk3.ch.intel.com> In-Reply-To: <150169902310.59677.18062301799811367806.stgit@djiang5-desk3.ch.intel.com> References: <150169902310.59677.18062301799811367806.stgit@djiang5-desk3.ch.intel.com> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 Sender: dmaengine-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: dmaengine@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Adding blk-mq support to the pmem driver in addition to the direct bio support. This allows for hardware offloading via DMA engines. By default the bio method will be enabled. The blk-mq support can be turned on via module parameter queue_mode=1. Signed-off-by: Dave Jiang Reviewed-by: Ross Zwisler --- drivers/nvdimm/pmem.c | 137 +++++++++++++++++++++++++++++++++++++++++-------- drivers/nvdimm/pmem.h | 3 + 2 files changed, 119 insertions(+), 21 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe dmaengine" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index c544d46..98e752f 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -31,10 +31,24 @@ #include #include #include +#include #include "pmem.h" #include "pfn.h" #include "nd.h" +enum { + PMEM_Q_BIO = 0, + PMEM_Q_MQ = 1, +}; + +static int queue_mode = PMEM_Q_BIO; +module_param(queue_mode, int, 0444); +MODULE_PARM_DESC(queue_mode, "Pmem Queue Mode (0=BIO, 1=BLK-MQ)"); + +struct pmem_cmd { + struct request *rq; +}; + static struct device *to_dev(struct pmem_device *pmem) { /* @@ -239,9 +253,13 @@ static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, }; -static void pmem_release_queue(void *q) +static void pmem_release_queue(void *data) { - blk_cleanup_queue(q); + struct pmem_device *pmem = (struct pmem_device *)data; + + blk_cleanup_queue(pmem->q); + if (queue_mode == PMEM_Q_MQ) + blk_mq_free_tag_set(&pmem->tag_set); } static void pmem_freeze_queue(void *q) @@ -259,6 +277,54 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); } +static int pmem_handle_cmd(struct pmem_cmd *cmd) +{ + struct request *req = cmd->rq; + struct request_queue *q = req->q; + struct pmem_device *pmem = q->queuedata; + struct nd_region *nd_region = to_region(pmem); + struct bio_vec bvec; + struct req_iterator iter; + int rc = 0; + + if (req->cmd_flags & REQ_FLUSH) + nvdimm_flush(nd_region); + + rq_for_each_segment(bvec, req, iter) { + rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, + bvec.bv_offset, op_is_write(req_op(req)), + iter.iter.bi_sector); + if (rc < 0) + break; + } + + if (req->cmd_flags & REQ_FUA) + nvdimm_flush(nd_region); + + blk_mq_end_request(cmd->rq, rc); + + return rc; +} + +static int pmem_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct pmem_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); + + cmd->rq = bd->rq; + + blk_mq_start_request(bd->rq); + + if (pmem_handle_cmd(cmd) < 0) + return BLK_MQ_RQ_QUEUE_ERROR; + else + return BLK_MQ_RQ_QUEUE_OK; +} + +static const struct blk_mq_ops pmem_mq_ops = { + .queue_rq = pmem_queue_rq, +}; + static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { @@ -272,9 +338,9 @@ static int pmem_attach_disk(struct device *dev, struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; struct resource pfn_res; - struct request_queue *q; struct gendisk *disk; void *addr; + int rc; /* while nsio_rw_bytes is active, parse a pfn info block if present */ if (is_nd_pfn(dev)) { @@ -303,17 +369,47 @@ static int pmem_attach_disk(struct device *dev, return -EBUSY; } - q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev)); - if (!q) - return -ENOMEM; + if (queue_mode == PMEM_Q_MQ) { + pmem->tag_set.ops = &pmem_mq_ops; + pmem->tag_set.nr_hw_queues = nr_online_nodes; + pmem->tag_set.queue_depth = 64; + pmem->tag_set.numa_node = dev_to_node(dev); + pmem->tag_set.cmd_size = sizeof(struct pmem_cmd); + pmem->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + pmem->tag_set.driver_data = pmem; + + rc = blk_mq_alloc_tag_set(&pmem->tag_set); + if (rc < 0) + return rc; + + pmem->q = blk_mq_init_queue(&pmem->tag_set); + if (IS_ERR(pmem->q)) { + blk_mq_free_tag_set(&pmem->tag_set); + return -ENOMEM; + } - if (devm_add_action_or_reset(dev, pmem_release_queue, q)) - return -ENOMEM; + if (devm_add_action_or_reset(dev, pmem_release_queue, pmem)) { + blk_mq_free_tag_set(&pmem->tag_set); + return -ENOMEM; + } + } else if (queue_mode == PMEM_Q_BIO) { + pmem->q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev)); + if (!pmem->q) + return -ENOMEM; + + if (devm_add_action_or_reset(dev, pmem_release_queue, pmem)) + return -ENOMEM; + + blk_queue_make_request(pmem->q, pmem_make_request); + } else { + dev_warn(dev, "Invalid queue mode: %d\n", queue_mode); + return -EINVAL; + } pmem->pfn_flags = PFN_DEV; if (is_nd_pfn(dev)) { - addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter, - altmap); + addr = devm_memremap_pages(dev, &pfn_res, + &pmem->q->q_usage_counter, altmap); pfn_sb = nd_pfn->pfn_sb; pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res); @@ -322,7 +418,7 @@ static int pmem_attach_disk(struct device *dev, res->start += pmem->data_offset; } else if (pmem_should_map_pages(dev)) { addr = devm_memremap_pages(dev, &nsio->res, - &q->q_usage_counter, NULL); + &pmem->q->q_usage_counter, NULL); pmem->pfn_flags |= PFN_MAP; } else addr = devm_memremap(dev, pmem->phys_addr, @@ -332,21 +428,20 @@ static int pmem_attach_disk(struct device *dev, * At release time the queue must be frozen before * devm_memremap_pages is unwound */ - if (devm_add_action_or_reset(dev, pmem_freeze_queue, q)) + if (devm_add_action_or_reset(dev, pmem_freeze_queue, pmem->q)) return -ENOMEM; if (IS_ERR(addr)) return PTR_ERR(addr); pmem->virt_addr = addr; - blk_queue_write_cache(q, true, true); - blk_queue_make_request(q, pmem_make_request); - blk_queue_physical_block_size(q, PAGE_SIZE); - blk_queue_max_hw_sectors(q, UINT_MAX); - blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); - queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); - queue_flag_set_unlocked(QUEUE_FLAG_DAX, q); - q->queuedata = pmem; + blk_queue_write_cache(pmem->q, true, true); + blk_queue_physical_block_size(pmem->q, PAGE_SIZE); + blk_queue_max_hw_sectors(pmem->q, UINT_MAX); + blk_queue_bounce_limit(pmem->q, BLK_BOUNCE_ANY); + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, pmem->q); + queue_flag_set_unlocked(QUEUE_FLAG_DAX, pmem->q); + pmem->q->queuedata = pmem; disk = alloc_disk_node(0, nid); if (!disk) @@ -354,7 +449,7 @@ static int pmem_attach_disk(struct device *dev, pmem->disk = disk; disk->fops = &pmem_fops; - disk->queue = q; + disk->queue = pmem->q; disk->flags = GENHD_FL_EXT_DEVT; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h index 7f4dbd7..1836c7b 100644 --- a/drivers/nvdimm/pmem.h +++ b/drivers/nvdimm/pmem.h @@ -4,6 +4,7 @@ #include #include #include +#include /* this definition is in it's own header for tools/testing/nvdimm to consume */ struct pmem_device { @@ -20,6 +21,8 @@ struct pmem_device { struct badblocks bb; struct dax_device *dax_dev; struct gendisk *disk; + struct blk_mq_tag_set tag_set; + struct request_queue *q; }; long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,