Re: [PATCH v5 06/10] nvmet: add copy command support for bdev and file ns

[Nitesh Shetty <nj.shetty@samsung.com>]

[-- Attachment #1: Type: text/plain, Size: 10272 bytes --]

On Wed, Nov 23, 2022 at 04:17:41PM +0800, Guixin Liu wrote:
> 
> 在 2022/11/23 13:58, Nitesh Shetty 写道:
> > 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: 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 | 79 +++++++++++++++++++++++++++++++
> >   drivers/nvme/target/io-cmd-file.c | 51 ++++++++++++++++++++
> >   drivers/nvme/target/loop.c        |  6 +++
> >   drivers/nvme/target/nvmet.h       |  2 +
> >   5 files changed, 145 insertions(+), 2 deletions(-)
> > 
> > diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
> > index c8a061ce3ee5..5ae509ff4b19 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 +533,12 @@ 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 = (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..01f0160125fb 100644
> > --- a/drivers/nvme/target/io-cmd-bdev.c
> > +++ b/drivers/nvme/target/io-cmd-bdev.c
> > @@ -46,6 +46,19 @@ 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));
> > +
> > +	/*Copy limits*/
> > +	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(id->mssrl);
> > +	} else {
> > +		id->msrc = (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(id->mssrl);
> > +	}
> 
> Based on my understanding of the NVMe protocol 2.0,  the mssrl is the max
> length per single range entry,
> 
> the mcl is the total max copy length in one copy command, may I ask why mcl
> = msssrl? not mcl = mssrl * msrc?
> 
> Best Regards,
> 
> Guixin Liu
>

You are right, as per NVMe spec, mcl >= mssrl. Since we decided to make
copy offload generic for NVMe/Xcopy/copy across namespaces and all, we went
with 2 bio/bdev design, which is compatible with device mapper.
So effectively we are using 1 range(msrc), when using only 1 range, I
feel it makes sense to use one of the limits, so went with mssrl.

Thanks,
Nitesh

> >   }
> >   void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
> > @@ -184,6 +197,23 @@ static void nvmet_bio_done(struct bio *bio)
> >   	nvmet_req_bio_put(req, bio);
> >   }
> > +static void nvmet_bdev_copy_end_io(void *private, int status)
> > +{
> > +	struct nvmet_req *req = (struct nvmet_req *)private;
> > +	int id;
> > +
> > +	if (status) {
> > +		for (id = 0 ; id < req->nr_range; id++) {
> > +			if (req->ranges[id].len != req->ranges[id].comp_len) {
> > +				req->cqe->result.u32 = cpu_to_le32(id);
> > +				break;
> > +			}
> > +		}
> > +	}
> > +	kfree(req->ranges);
> > +	nvmet_req_complete(req, errno_to_nvme_status(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 +480,51 @@ 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 *ranges;
> > +	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;
> > +	ranges = kmalloc_array(nr_range, sizeof(*ranges), 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;
> > +
> > +		ranges[id].dst = dest + dest_off;
> > +		ranges[id].src = le64_to_cpu(range.slba) <<
> > +					req->ns->blksize_shift;
> > +		ranges[id].len = (le16_to_cpu(range.nlb) + 1) <<
> > +					req->ns->blksize_shift;
> > +		ranges[id].comp_len = 0;
> > +		dest_off += ranges[id].len;
> > +	}
> > +	req->ranges = ranges;
> > +	req->nr_range = nr_range;
> > +	ret = blkdev_issue_copy(req->ns->bdev, req->ns->bdev, ranges, nr_range,
> > +			nvmet_bdev_copy_end_io, (void *)req, GFP_KERNEL);
> > +	if (ret) {
> > +		for (id = 0 ; id < nr_range; id++) {
> > +			if (ranges[id].len != ranges[id].comp_len) {
> > +				req->cqe->result.u32 = cpu_to_le32(id);
> > +				break;
> > +			}
> > +		}
> > +		goto out;
> > +	} else
> > +		return;
> > +out:
> > +	kfree(ranges);
> > +	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) {
> > @@ -468,6 +543,10 @@ 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 64b47e2a4633..a81d38796e17 100644
> > --- a/drivers/nvme/target/io-cmd-file.c
> > +++ b/drivers/nvme/target/io-cmd-file.c
> > @@ -338,6 +338,48 @@ 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 +388,12 @@ 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);
> > @@ -392,6 +440,9 @@ 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 b45fe3adf015..55802632b407 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;
> >   	blk_mq_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 dfe3894205aa..3b4c7d2ee45d 100644
> > --- a/drivers/nvme/target/nvmet.h
> > +++ b/drivers/nvme/target/nvmet.h
> > @@ -391,6 +391,8 @@ struct nvmet_req {
> >   	struct device		*p2p_client;
> >   	u16			error_loc;
> >   	u64			error_slba;
> > +	struct range_entry *ranges;
> > +	unsigned int nr_range;
> >   };
> >   extern struct workqueue_struct *buffered_io_wq;

[-- Attachment #2: Type: text/plain, Size: 0 bytes --]