Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Nitesh Shetty <nj.shetty@samsung.com>
To:     Jens Axboe <axboe@kernel.dk>, Jonathan Corbet <corbet@lwn.net>,
        Alasdair Kergon <agk@redhat.com>,
        Mike Snitzer <snitzer@kernel.org>, dm-devel@redhat.com,
        Keith Busch <kbusch@kernel.org>,
        Christoph Hellwig <hch@lst.de>,
        Sagi Grimberg <sagi@grimberg.me>,
        James Smart <james.smart@broadcom.com>,
        Chaitanya Kulkarni <kch@nvidia.com>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Christian Brauner <brauner@kernel.org>
Cc:     martin.petersen@oracle.com, linux-scsi@vger.kernel.org,
        willy@infradead.org, hare@suse.de, djwong@kernel.org,
        bvanassche@acm.org, ming.lei@redhat.com, dlemoal@kernel.org,
        nitheshshetty@gmail.com, gost.dev@samsung.com,
        Nitesh Shetty <nj.shetty@samsung.com>,
        Anuj Gupta <anuj20.g@samsung.com>, linux-block@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
        linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH v12 6/9] nvmet: add copy command support for bdev and file
 ns
Date:   Mon,  5 Jun 2023 17:47:22 +0530
Message-Id: <20230605121732.28468-7-nj.shetty@samsung.com>
In-Reply-To: <20230605121732.28468-1-nj.shetty@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 105P
DLP-Filter: Pass
References: <20230605121732.28468-1-nj.shetty@samsung.com>
        <CGME20230605122330epcas5p18a452356d5bc39b852b85304bac5b0cc@epcas5p1.samsung.com>
Precedence: bulk

Add support for handling nvme_cmd_copy command on target.
For bdev-ns we call into blkdev_issue_copy, which the block layer
completes by a offloaded copy request to backend bdev or by emulating the
request.

For file-ns we call vfs_copy_file_range to service our request.

Currently target always shows copy capability by setting
NVME_CTRL_ONCS_COPY in controller ONCS.

loop target has copy support, which can be used to test copy offload.

Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
---
 drivers/nvme/target/admin-cmd.c   |  9 ++++-
 drivers/nvme/target/io-cmd-bdev.c | 62 +++++++++++++++++++++++++++++++
 drivers/nvme/target/io-cmd-file.c | 52 ++++++++++++++++++++++++++
 drivers/nvme/target/loop.c        |  6 +++
 drivers/nvme/target/nvmet.h       |  1 +
 5 files changed, 128 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 39cb570f833d..8e644b8ec0fd 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -433,8 +433,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
-			NVME_CTRL_ONCS_WRITE_ZEROES);
-
+			NVME_CTRL_ONCS_WRITE_ZEROES | NVME_CTRL_ONCS_COPY);
 	/* XXX: don't report vwc if the underlying device is write through */
 	id->vwc = NVME_CTRL_VWC_PRESENT;
 
@@ -536,6 +535,12 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 
 	if (req->ns->bdev)
 		nvmet_bdev_set_limits(req->ns->bdev, id);
+	else {
+		id->msrc = (__force u8)to0based(BIO_MAX_VECS - 1);
+		id->mssrl = cpu_to_le16(BIO_MAX_VECS <<
+				(PAGE_SHIFT - SECTOR_SHIFT));
+		id->mcl = cpu_to_le32(le16_to_cpu(id->mssrl));
+	}
 
 	/*
 	 * We just provide a single LBA format that matches what the
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index c2d6cea0236b..92b5accf0743 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -46,6 +46,18 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 	id->npda = id->npdg;
 	/* NOWS = Namespace Optimal Write Size */
 	id->nows = to0based(bdev_io_opt(bdev) / bdev_logical_block_size(bdev));
+
+	if (bdev_max_copy_sectors(bdev)) {
+		id->msrc = id->msrc;
+		id->mssrl = cpu_to_le16((bdev_max_copy_sectors(bdev) <<
+				SECTOR_SHIFT) / bdev_logical_block_size(bdev));
+		id->mcl = cpu_to_le32((__force u32)id->mssrl);
+	} else {
+		id->msrc = (__force u8)to0based(BIO_MAX_VECS - 1);
+		id->mssrl = cpu_to_le16((BIO_MAX_VECS << PAGE_SHIFT) /
+				bdev_logical_block_size(bdev));
+		id->mcl = cpu_to_le32((__force u32)id->mssrl);
+	}
 }
 
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
@@ -184,6 +196,21 @@ static void nvmet_bio_done(struct bio *bio)
 	nvmet_req_bio_put(req, bio);
 }
 
+static void nvmet_bdev_copy_end_io(void *private, int comp_len)
+{
+	struct nvmet_req *req = (struct nvmet_req *)private;
+	u16 status;
+
+	if (comp_len == req->copy_len) {
+		req->cqe->result.u32 = cpu_to_le32(1);
+		status = errno_to_nvme_status(req, 0);
+	} else {
+		req->cqe->result.u32 = cpu_to_le32(0);
+		status = errno_to_nvme_status(req, (__force u16)BLK_STS_IOERR);
+	}
+	nvmet_req_complete(req, status);
+}
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio,
 				struct sg_mapping_iter *miter)
@@ -450,6 +477,37 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 	}
 }
 
+/* At present we handle only one range entry, since copy offload is aligned with
+ * copy_file_range, only one entry is passed from block layer.
+ */
+static void nvmet_bdev_execute_copy(struct nvmet_req *req)
+{
+	struct nvme_copy_range range;
+	struct nvme_command *cmd = req->cmd;
+	ssize_t ret;
+	u16 status;
+
+	status = nvmet_copy_from_sgl(req, 0, &range, sizeof(range));
+	if (status)
+		goto out;
+
+	ret = blkdev_copy_offload(req->ns->bdev,
+		le64_to_cpu(cmd->copy.sdlba) << req->ns->blksize_shift,
+		req->ns->bdev,
+		le64_to_cpu(range.slba) << req->ns->blksize_shift,
+		(le16_to_cpu(range.nlb) + 1) << req->ns->blksize_shift,
+		nvmet_bdev_copy_end_io, (void *)req, GFP_KERNEL);
+	if (ret) {
+		req->cqe->result.u32 = cpu_to_le32(0);
+		status = blk_to_nvme_status(req, BLK_STS_IOERR);
+		goto out;
+	}
+
+	return;
+out:
+	nvmet_req_complete(req, errno_to_nvme_status(req, status));
+}
+
 u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 {
 	switch (req->cmd->common.opcode) {
@@ -468,6 +526,10 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_bdev_execute_write_zeroes;
 		return 0;
+	case nvme_cmd_copy:
+		req->execute = nvmet_bdev_execute_copy;
+		return 0;
+
 	default:
 		return nvmet_report_invalid_opcode(req);
 	}
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 2d068439b129..f61aa834f7a5 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -322,6 +322,49 @@ static void nvmet_file_dsm_work(struct work_struct *w)
 	}
 }
 
+static void nvmet_file_copy_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+	int nr_range = req->cmd->copy.nr_range + 1;
+	u16 status = 0;
+	int src, id;
+	ssize_t len, ret;
+	loff_t pos;
+
+	pos = le64_to_cpu(req->cmd->copy.sdlba) << req->ns->blksize_shift;
+	if (unlikely(pos + req->transfer_len > req->ns->size)) {
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
+		return;
+	}
+
+	for (id = 0 ; id < nr_range; id++) {
+		struct nvme_copy_range range;
+
+		status = nvmet_copy_from_sgl(req, id * sizeof(range), &range,
+					sizeof(range));
+		if (status)
+			goto out;
+
+		src = (le64_to_cpu(range.slba) << (req->ns->blksize_shift));
+		len = (le16_to_cpu(range.nlb) + 1) << (req->ns->blksize_shift);
+		ret = vfs_copy_file_range(req->ns->file, src, req->ns->file,
+					pos, len, 0);
+		if (ret != len) {
+			pos += ret;
+			req->cqe->result.u32 = cpu_to_le32(id);
+			if (ret < 0)
+				status = errno_to_nvme_status(req, ret);
+			else
+				status = errno_to_nvme_status(req, -EIO);
+			goto out;
+		} else
+			pos += len;
+	}
+
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_file_execute_dsm(struct nvmet_req *req)
 {
 	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
@@ -330,6 +373,12 @@ static void nvmet_file_execute_dsm(struct nvmet_req *req)
 	queue_work(nvmet_wq, &req->f.work);
 }
 
+static void nvmet_file_execute_copy(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_copy_work);
+	queue_work(nvmet_wq, &req->f.work);
+}
+
 static void nvmet_file_write_zeroes_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
@@ -376,6 +425,9 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_file_execute_write_zeroes;
 		return 0;
+	case nvme_cmd_copy:
+		req->execute = nvmet_file_execute_copy;
+		return 0;
 	default:
 		return nvmet_report_invalid_opcode(req);
 	}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index f2d24b2d992f..d18ed8067a15 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -146,6 +146,12 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return ret;
 
 	nvme_start_request(req);
+	if (unlikely((req->cmd_flags & REQ_COPY) &&
+				(req_op(req) == REQ_OP_READ))) {
+		blk_mq_set_request_complete(req);
+		blk_mq_end_request(req, BLK_STS_OK);
+		return BLK_STS_OK;
+	}
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
 	iod->req.port = queue->ctrl->port;
 	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index dc60a22646f7..1615dc9194ba 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -393,6 +393,7 @@ struct nvmet_req {
 	struct device		*p2p_client;
 	u16			error_loc;
 	u64			error_slba;
+	size_t			copy_len;
 };
 
 #define NVMET_MAX_MPOOL_BVEC		16
-- 
2.35.1.500.gb896f729e2