nvme: add copy offload support

For device supporting native copy, nvme driver receives read and
write request with BLK_COPY op flags.
For read request the nvme driver populates the payload with source
information.
For write request the driver converts it to nvme copy command using the
source information in the payload and submits to the device.
current design only supports single source range.
This design is courtesy Mikulas Patocka's token based copy

trace event support for nvme_copy_cmd.
Set the device copy limits to queue limits.

Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Javier González <javier.gonz@samsung.com>
Signed-off-by: Arnav Dawn <arnav.dawn@samsung.com>

drivers/nvme/host/core.c

@@ -724,6 +724,87 @@ static inline void nvme_setup_flush(struct nvme_ns *ns,
 	cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
 }
 
+static inline blk_status_t nvme_setup_copy_read(struct nvme_ns *ns, struct request *req)
+{
+	struct bio *bio = req->bio;
+	struct nvme_copy_token *token = bvec_kmap_local(&bio->bi_io_vec[0]);
+
+	memcpy(token->subsys, "nvme", 4);
+	token->ns = ns;
+	token->src_sector = bio->bi_iter.bi_sector;
+	token->sectors = bio->bi_iter.bi_size >> 9;
+
+	return BLK_STS_OK;
+}
+
+static inline blk_status_t nvme_setup_copy_write(struct nvme_ns *ns,
+	       struct request *req, struct nvme_command *cmnd)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	struct nvme_copy_range *range = NULL;
+	struct bio *bio = req->bio;
+	struct nvme_copy_token *token = bvec_kmap_local(&bio->bi_io_vec[0]);
+	sector_t src_sector, dst_sector, n_sectors;
+	u64 src_lba, dst_lba, n_lba;
+	unsigned short nr_range = 1;
+	u16 control = 0;
+	u32 dsmgmt = 0;
+
+	if (unlikely(memcmp(token->subsys, "nvme", 4)))
+		return BLK_STS_NOTSUPP;
+	if (unlikely(token->ns != ns))
+		return BLK_STS_NOTSUPP;
+
+	src_sector = token->src_sector;
+	dst_sector = bio->bi_iter.bi_sector;
+	n_sectors = token->sectors;
+	if (WARN_ON(n_sectors != bio->bi_iter.bi_size >> 9))
+		return BLK_STS_NOTSUPP;
+
+	src_lba = nvme_sect_to_lba(ns, src_sector);
+	dst_lba = nvme_sect_to_lba(ns, dst_sector);
+	n_lba = nvme_sect_to_lba(ns, n_sectors);
+
+	if (unlikely(nvme_lba_to_sect(ns, src_lba) != src_sector) ||
+			unlikely(nvme_lba_to_sect(ns, dst_lba) != dst_sector) ||
+			unlikely(nvme_lba_to_sect(ns, n_lba) != n_sectors))
+		return BLK_STS_NOTSUPP;
+
+	if (WARN_ON(!n_lba))
+		return BLK_STS_NOTSUPP;
+
+	if (req->cmd_flags & REQ_FUA)
+		control |= NVME_RW_FUA;
+
+	if (req->cmd_flags & REQ_FAILFAST_DEV)
+		control |= NVME_RW_LR;
+
+	memset(cmnd, 0, sizeof(*cmnd));
+	cmnd->copy.opcode = nvme_cmd_copy;
+	cmnd->copy.nsid = cpu_to_le32(ns->head->ns_id);
+	cmnd->copy.sdlba = cpu_to_le64(dst_lba);
+
+	range = kmalloc_array(nr_range, sizeof(*range),
+			GFP_ATOMIC | __GFP_NOWARN);
+	if (!range)
+		return BLK_STS_RESOURCE;
+
+	range[0].slba = cpu_to_le64(src_lba);
+	range[0].nlb = cpu_to_le16(n_lba - 1);
+
+	cmnd->copy.nr_range = 0;
+
+	req->special_vec.bv_page = virt_to_page(range);
+	req->special_vec.bv_offset = offset_in_page(range);
+	req->special_vec.bv_len = sizeof(*range) * nr_range;
+	req->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+	cmnd->copy.control = cpu_to_le16(control);
+	cmnd->copy.dspec = cpu_to_le32(dsmgmt);
+
+	return BLK_STS_OK;
+}
+
 static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmnd)
 {
@@ -947,10 +1028,16 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 		ret = nvme_setup_discard(ns, req, cmd);
 		break;
 	case REQ_OP_READ:
-		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
+		if (unlikely(req->cmd_flags & REQ_COPY))
+			ret = nvme_setup_copy_read(ns, req);
+		else
+			ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
 		break;
 	case REQ_OP_WRITE:
-		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
+		if (unlikely(req->cmd_flags & REQ_COPY))
+			ret = nvme_setup_copy_write(ns, req, cmd);
+		else
+			ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
 		break;
 	case REQ_OP_ZONE_APPEND:
 		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
@@ -1642,6 +1729,29 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
 }
 
+static void nvme_config_copy(struct gendisk *disk, struct nvme_ns *ns,
+				       struct nvme_id_ns *id)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	struct request_queue *q = disk->queue;
+
+	if (!(ctrl->oncs & NVME_CTRL_ONCS_COPY)) {
+		blk_queue_max_copy_sectors(q, 0);
+		blk_queue_max_copy_range_sectors(q, 0);
+		blk_queue_max_copy_nr_ranges(q, 0);
+		blk_queue_flag_clear(QUEUE_FLAG_COPY, q);
+		return;
+	}
+
+	/* setting copy limits */
+	if (blk_queue_flag_test_and_set(QUEUE_FLAG_COPY, q))
+		return;
+
+	blk_queue_max_copy_sectors(q, nvme_lba_to_sect(ns, le32_to_cpu(id->mcl)));
+	blk_queue_max_copy_range_sectors(q, nvme_lba_to_sect(ns, le16_to_cpu(id->mssrl)));
+	blk_queue_max_copy_nr_ranges(q, id->msrc + 1);
+}
+
 static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 {
 	return uuid_equal(&a->uuid, &b->uuid) &&
@@ -1841,6 +1951,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	set_capacity_and_notify(disk, capacity);
 
 	nvme_config_discard(disk, ns);
+	nvme_config_copy(disk, ns, id);
 	blk_queue_max_write_zeroes_sectors(disk->queue,
 					   ns->ctrl->max_zeroes_sectors);
 }
@@ -4833,6 +4944,7 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_download_firmware) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_dsm_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_copy_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_write_zeroes_cmd) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_get_log_page_command) != 64);

drivers/nvme/host/fc.c

@@ -2788,6 +2788,10 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (ret)
 		return ret;
 
+	if (unlikely((rq->cmd_flags & REQ_COPY) && (req_op(rq) == REQ_OP_READ))) {
+		blk_mq_end_request(rq, BLK_STS_OK);
+		return BLK_STS_OK;
+	}
 	/*
 	 * nvme core doesn't quite treat the rq opaquely. Commands such
 	 * as WRITE ZEROES will return a non-zero rq payload_bytes yet

drivers/nvme/host/nvme.h

@@ -482,6 +482,13 @@ struct nvme_ns {
 
 };
 
+struct nvme_copy_token {
+	char subsys[4];
+	struct nvme_ns *ns;
+	u64 src_sector;
+	u64 sectors;
+};
+
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
 static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
 {

drivers/nvme/host/pci.c

@@ -511,6 +511,14 @@ static inline void nvme_sq_copy_cmd(struct nvme_queue *nvmeq,
 		nvmeq->sq_tail = 0;
 }
 
+static void nvme_commit_sqdb(struct nvme_queue *nvmeq)
+{
+	spin_lock(&nvmeq->sq_lock);
+	if (nvmeq->sq_tail != nvmeq->last_sq_tail)
+		nvme_write_sq_db(nvmeq, true);
+	spin_unlock(&nvmeq->sq_lock);
+}
+
 static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
 {
 	struct nvme_queue *nvmeq = hctx->driver_data;
@@ -918,6 +926,11 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	if (ret)
 		return ret;
 
+	if (unlikely((req->cmd_flags & REQ_COPY) && (req_op(req) == REQ_OP_READ))) {
+		blk_mq_start_request(req);
+		return BLK_STS_OK;
+	}
+
 	if (blk_rq_nr_phys_segments(req)) {
 		ret = nvme_map_data(dev, req, &iod->cmd);
 		if (ret)
@@ -931,6 +944,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	}
 
 	blk_mq_start_request(req);
+
 	return BLK_STS_OK;
 out_unmap_data:
 	nvme_unmap_data(dev, req);
@@ -964,6 +978,17 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	ret = nvme_prep_rq(dev, req);
 	if (unlikely(ret))
 		return ret;
+	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);
+		/* Commit the sq if copy read was the last req in the list,
+		 * as copy read deoesn't update sq db
+		 */
+		if (bd->last)
+			nvme_commit_sqdb(nvmeq);
+		return ret;
+	}
+
 	spin_lock(&nvmeq->sq_lock);
 	nvme_sq_copy_cmd(nvmeq, &iod->cmd);
 	nvme_write_sq_db(nvmeq, bd->last);

drivers/nvme/host/rdma.c

@@ -2087,6 +2087,12 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (ret)
 		goto unmap_qe;
 
+	if (unlikely((rq->cmd_flags & REQ_COPY) && (req_op(rq) == REQ_OP_READ))) {
+		blk_mq_end_request(rq, BLK_STS_OK);
+		ret = BLK_STS_OK;
+		goto unmap_qe;
+	}
+
 	blk_mq_start_request(rq);
 
 	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&

drivers/nvme/host/tcp.c

@@ -2394,6 +2394,11 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+	if (unlikely((rq->cmd_flags & REQ_COPY) && (req_op(rq) == REQ_OP_READ))) {
+		blk_mq_start_request(req);
+		return BLK_STS_OK;
+	}
+
 	req->state = NVME_TCP_SEND_CMD_PDU;
 	req->status = cpu_to_le16(NVME_SC_SUCCESS);
 	req->offset = 0;
@@ -2462,6 +2467,15 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(rq);
 
+	if (unlikely((rq->cmd_flags & REQ_COPY) && (req_op(rq) == REQ_OP_READ))) {
+		blk_mq_set_request_complete(rq);
+		blk_mq_end_request(rq, BLK_STS_OK);
+		/* if copy read is the last req queue tcp reqs */
+		if (bd->last && nvme_tcp_queue_more(queue))
+			queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
+		return ret;
+	}
+
 	nvme_tcp_queue_request(req, true, bd->last);
 
 	return BLK_STS_OK;

drivers/nvme/host/trace.c

@@ -150,6 +150,23 @@ static const char *nvme_trace_read_write(struct trace_seq *p, u8 *cdw10)
 	return ret;
 }
 
+static const char *nvme_trace_copy(struct trace_seq *p, u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u64 slba = get_unaligned_le64(cdw10);
+	u8 nr_range = get_unaligned_le16(cdw10 + 8);
+	u16 control = get_unaligned_le16(cdw10 + 10);
+	u32 dsmgmt = get_unaligned_le32(cdw10 + 12);
+	u32 reftag = get_unaligned_le32(cdw10 +  16);
+
+	trace_seq_printf(p,
+			 "slba=%llu, nr_range=%u, ctrl=0x%x, dsmgmt=%u, reftag=%u",
+			 slba, nr_range, control, dsmgmt, reftag);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvme_trace_dsm(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -243,6 +260,8 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
 		return nvme_trace_zone_mgmt_send(p, cdw10);
 	case nvme_cmd_zone_mgmt_recv:
 		return nvme_trace_zone_mgmt_recv(p, cdw10);
+	case nvme_cmd_copy:
+		return nvme_trace_copy(p, cdw10);
 	default:
 		return nvme_trace_common(p, cdw10);
 	}

include/linux/nvme.h

@@ -316,7 +316,7 @@ struct nvme_id_ctrl {
 	__u8			nvscc;
 	__u8			nwpc;
 	__le16			acwu;
-	__u8			rsvd534[2];
+	__le16			ocfs;
 	__le32			sgls;
 	__le32			mnan;
 	__u8			rsvd544[224];
@@ -344,6 +344,7 @@ enum {
 	NVME_CTRL_ONCS_WRITE_ZEROES		= 1 << 3,
 	NVME_CTRL_ONCS_RESERVATIONS		= 1 << 5,
 	NVME_CTRL_ONCS_TIMESTAMP		= 1 << 6,
+	NVME_CTRL_ONCS_COPY			= 1 << 8,
 	NVME_CTRL_VWC_PRESENT			= 1 << 0,
 	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
 	NVME_CTRL_OACS_NS_MNGT_SUPP		= 1 << 3,
@@ -393,7 +394,10 @@ struct nvme_id_ns {
 	__le16			npdg;
 	__le16			npda;
 	__le16			nows;
-	__u8			rsvd74[18];
+	__le16			mssrl;
+	__le32			mcl;
+	__u8			msrc;
+	__u8			rsvd91[11];
 	__le32			anagrpid;
 	__u8			rsvd96[3];
 	__u8			nsattr;
@@ -750,6 +754,7 @@ enum nvme_opcode {
 	nvme_cmd_resv_report	= 0x0e,
 	nvme_cmd_resv_acquire	= 0x11,
 	nvme_cmd_resv_release	= 0x15,
+	nvme_cmd_copy		= 0x19,
 	nvme_cmd_zone_mgmt_send	= 0x79,
 	nvme_cmd_zone_mgmt_recv	= 0x7a,
 	nvme_cmd_zone_append	= 0x7d,
@@ -771,7 +776,8 @@ enum nvme_opcode {
 		nvme_opcode_name(nvme_cmd_resv_release),	\
 		nvme_opcode_name(nvme_cmd_zone_mgmt_send),	\
 		nvme_opcode_name(nvme_cmd_zone_mgmt_recv),	\
-		nvme_opcode_name(nvme_cmd_zone_append))
+		nvme_opcode_name(nvme_cmd_zone_append),		\
+		nvme_opcode_name(nvme_cmd_copy))
 
 
 
@@ -945,6 +951,36 @@ struct nvme_dsm_range {
 	__le64			slba;
 };
 
+struct nvme_copy_command {
+	__u8                    opcode;
+	__u8                    flags;
+	__u16                   command_id;
+	__le32                  nsid;
+	__u64                   rsvd2;
+	__le64                  metadata;
+	union nvme_data_ptr     dptr;
+	__le64                  sdlba;
+	__u8			nr_range;
+	__u8			rsvd12;
+	__le16                  control;
+	__le16                  rsvd13;
+	__le16			dspec;
+	__le32                  ilbrt;
+	__le16                  lbat;
+	__le16                  lbatm;
+};
+
+struct nvme_copy_range {
+	__le64			rsvd0;
+	__le64			slba;
+	__le16			nlb;
+	__le16			rsvd18;
+	__le32			rsvd20;
+	__le32			eilbrt;
+	__le16			elbat;
+	__le16			elbatm;
+};
+
 struct nvme_write_zeroes_cmd {
 	__u8			opcode;
 	__u8			flags;
@@ -1499,6 +1535,7 @@ struct nvme_command {
 		struct nvme_download_firmware dlfw;
 		struct nvme_format_cmd format;
 		struct nvme_dsm_cmd dsm;
+		struct nvme_copy_command copy;
 		struct nvme_write_zeroes_cmd write_zeroes;
 		struct nvme_zone_mgmt_send_cmd zms;
 		struct nvme_zone_mgmt_recv_cmd zmr;