Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   Nitesh Shetty <nj.shetty@samsung.com>
Cc:     chaitanyak@nvidia.com, linux-block@vger.kernel.org,
        linux-scsi@vger.kernel.org, dm-devel@redhat.com,
        linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org,
        axboe@kernel.dk, msnitzer@redhat.com, bvanassche@acm.org,
        martin.petersen@oracle.com, hare@suse.de, kbusch@kernel.org,
        hch@lst.de, Frederick.Knight@netapp.com, osandov@fb.com,
        lsf-pc@lists.linux-foundation.org, djwong@kernel.org,
        josef@toxicpanda.com, clm@fb.com, dsterba@suse.com, tytso@mit.edu,
        jack@suse.com, nitheshshetty@gmail.com, gost.dev@samsung.com,
        Arnav Dawn <arnav.dawn@samsung.com>,
        Nitesh Shetty <nj.shetty@samsung.com>,
        Alasdair Kergon <agk@redhat.com>,
        Mike Snitzer <snitzer@kernel.org>,
        Sagi Grimberg <sagi@grimberg.me>,
        James Smart <james.smart@broadcom.com>,
        Chaitanya Kulkarni <kch@nvidia.com>,
        Damien Le Moal <damien.lemoal@opensource.wdc.com>,
        Naohiro Aota <naohiro.aota@wdc.com>,
        Johannes Thumshirn <jth@kernel.org>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        linux-kernel@vger.kernel.org
Subject: [PATCH v4 06/10] nvmet: add copy command support for bdev and file
 ns
Date:   Tue, 26 Apr 2022 15:42:34 +0530
Message-Id: <20220426101241.30100-7-nj.shetty@samsung.com>
In-Reply-To: <20220426101241.30100-1-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: <20220426101241.30100-1-nj.shetty@samsung.com>
        <CGME20220426102009epcas5p3e5b1ddfd5d3c7200972cecb139650da6@epcas5p3.samsung.com>
To:     unlisted-recipients:; (no To-header on input)
Precedence: bulk

From: Arnav Dawn <arnav.dawn@samsung.com>

Add support for handling target 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.

Signed-off-by: Arnav Dawn <arnav.dawn@samsung.com>
Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
---
 drivers/nvme/host/tcp.c           |  2 +-
 drivers/nvme/target/admin-cmd.c   |  8 +++-
 drivers/nvme/target/io-cmd-bdev.c | 65 +++++++++++++++++++++++++++++++
 drivers/nvme/target/io-cmd-file.c | 49 +++++++++++++++++++++++
 4 files changed, 121 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4e4cdcf8210a..2c77e5b596bb 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2395,7 +2395,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 		return ret;
 
 	if (unlikely((rq->cmd_flags & REQ_COPY) && (req_op(rq) == REQ_OP_READ))) {
-		blk_mq_start_request(req);
+		blk_mq_start_request(rq);
 		return BLK_STS_OK;
 	}
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 397daaf51f1b..db32debdb528 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -431,8 +431,7 @@ 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;
 
@@ -534,6 +533,11 @@ 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 = to0based(BIO_MAX_VECS);
+		id->mssrl = cpu_to_le16(BIO_MAX_VECS << (PAGE_SHIFT - SECTOR_SHIFT));
+		id->mcl = cpu_to_le32(le16_to_cpu(id->mssrl) * BIO_MAX_VECS);
+	}
 
 	/*
 	 * 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 27a72504d31c..18666d36423f 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -47,6 +47,30 @@ 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(ql->io_opt / ql->logical_block_size);
+
+	/*Copy limits*/
+	if (ql->max_copy_sectors) {
+		id->mcl = cpu_to_le32((ql->max_copy_sectors << 9) / ql->logical_block_size);
+		id->mssrl = cpu_to_le16((ql->max_copy_range_sectors << 9) /
+				ql->logical_block_size);
+		id->msrc = to0based(ql->max_copy_nr_ranges);
+	} else {
+		if (ql->zoned == BLK_ZONED_NONE) {
+			id->msrc = to0based(BIO_MAX_VECS);
+			id->mssrl = cpu_to_le16(
+					(BIO_MAX_VECS << PAGE_SHIFT) / ql->logical_block_size);
+			id->mcl = cpu_to_le32(le16_to_cpu(id->mssrl) * BIO_MAX_VECS);
+#ifdef CONFIG_BLK_DEV_ZONED
+		} else {
+			/* TODO: get right values for zoned device */
+			id->msrc = to0based(BIO_MAX_VECS);
+			id->mssrl = cpu_to_le16(min((BIO_MAX_VECS << PAGE_SHIFT),
+					ql->chunk_sectors) / ql->logical_block_size);
+			id->mcl = cpu_to_le32(min(le16_to_cpu(id->mssrl) * BIO_MAX_VECS,
+						ql->chunk_sectors));
+#endif
+		}
+	}
 }
 
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
@@ -442,6 +466,43 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 	}
 }
 
+static void nvmet_bdev_execute_copy(struct nvmet_req *req)
+{
+	struct nvme_copy_range range;
+	struct range_entry *rlist;
+	struct nvme_command *cmnd = req->cmd;
+	sector_t dest, dest_off = 0;
+	int ret, id, nr_range;
+
+	nr_range = cmnd->copy.nr_range + 1;
+	dest = le64_to_cpu(cmnd->copy.sdlba) << req->ns->blksize_shift;
+	rlist = kmalloc_array(nr_range, sizeof(*rlist), GFP_KERNEL);
+
+	for (id = 0 ; id < nr_range; id++) {
+		ret = nvmet_copy_from_sgl(req, id * sizeof(range), &range, sizeof(range));
+		if (ret)
+			goto out;
+
+		rlist[id].dst = dest + dest_off;
+		rlist[id].src = le64_to_cpu(range.slba) << req->ns->blksize_shift;
+		rlist[id].len = (le16_to_cpu(range.nlb) + 1) << req->ns->blksize_shift;
+		rlist[id].comp_len = 0;
+		dest_off += rlist[id].len;
+	}
+	ret = blkdev_issue_copy(req->ns->bdev, nr_range, rlist, req->ns->bdev, GFP_KERNEL);
+	if (ret) {
+		for (id = 0 ; id < nr_range; id++) {
+			if (rlist[id].len != rlist[id].comp_len) {
+				req->cqe->result.u32 = cpu_to_le32(id);
+				break;
+			}
+		}
+	}
+out:
+	kfree(rlist);
+	nvmet_req_complete(req, errno_to_nvme_status(req, ret));
+}
+
 u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 {
 	switch (req->cmd->common.opcode) {
@@ -460,6 +521,10 @@ 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 f3d58abf11e0..fe26a9120436 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -338,6 +338,46 @@ 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;
+	loff_t pos;
+	struct nvme_command *cmnd = req->cmd;
+	int ret = 0, len = 0, src, id;
+
+	nr_range = cmnd->copy.nr_range + 1;
+	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;
+
+		ret = nvmet_copy_from_sgl(req, id * sizeof(range), &range,
+					sizeof(range));
+		if (ret)
+			goto out;
+
+		len = (le16_to_cpu(range.nlb) + 1) << (req->ns->blksize_shift);
+		src = (le64_to_cpu(range.slba) << (req->ns->blksize_shift));
+		ret = vfs_copy_file_range(req->ns->file, src, req->ns->file, pos, len, 0);
+out:
+		if (ret != len) {
+			pos += ret;
+			req->cqe->result.u32 = cpu_to_le32(id);
+			nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) :
+					errno_to_nvme_status(req, -EIO));
+			return;
+
+		} else
+			pos += len;
+}
+	nvmet_req_complete(req, ret);
+
+}
 static void nvmet_file_execute_dsm(struct nvmet_req *req)
 {
 	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
@@ -346,6 +386,12 @@ 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);
+	schedule_work(&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);
@@ -392,6 +438,9 @@ 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);
 	}
-- 
2.35.1.500.gb896f729e2