[PATCH v3 8/9] engines/io_uring: Enable zone device support for io_uring_cmd I/O engine

[Ankit Kumar <ankit.kumar@samsung.com>]

Add zone device specific ioengine_ops for io_uring_cmd.
* get_zoned_model
* report_zones
* reset_wp
* get_max_open_zones

Add the necessary NVMe ZNS specfication opcodes and structures. Add
helper functions to submit admin and I/O passthrough commands for these
new NVMe ZNS specific commands.

For write workload iodepth must be set to 1 as there is no IO scheduler

Tested-by: Vincent Fu <vincent.fu@samsung.com>
Signed-off-by: Ankit Kumar <ankit.kumar@samsung.com>
---
 engines/io_uring.c |  32 ++++++
 engines/nvme.c     | 242 +++++++++++++++++++++++++++++++++++++++++++++
 engines/nvme.h     |  80 ++++++++++++++-
 3 files changed, 353 insertions(+), 1 deletion(-)

diff --git a/engines/io_uring.c b/engines/io_uring.c
index a7b7b166..5a5406d4 100644
--- a/engines/io_uring.c
+++ b/engines/io_uring.c
@@ -1164,6 +1164,34 @@ static int fio_ioring_cmd_get_file_size(struct thread_data *td,
 	return generic_get_file_size(td, f);
 }
 
+static int fio_ioring_cmd_get_zoned_model(struct thread_data *td,
+					  struct fio_file *f,
+					  enum zbd_zoned_model *model)
+{
+	return fio_nvme_get_zoned_model(td, f, model);
+}
+
+static int fio_ioring_cmd_report_zones(struct thread_data *td,
+				       struct fio_file *f, uint64_t offset,
+				       struct zbd_zone *zbdz,
+				       unsigned int nr_zones)
+{
+	return fio_nvme_report_zones(td, f, offset, zbdz, nr_zones);
+}
+
+static int fio_ioring_cmd_reset_wp(struct thread_data *td, struct fio_file *f,
+				   uint64_t offset, uint64_t length)
+{
+	return fio_nvme_reset_wp(td, f, offset, length);
+}
+
+static int fio_ioring_cmd_get_max_open_zones(struct thread_data *td,
+					     struct fio_file *f,
+					     unsigned int *max_open_zones)
+{
+	return fio_nvme_get_max_open_zones(td, f, max_open_zones);
+}
+
 static struct ioengine_ops ioengine_uring = {
 	.name			= "io_uring",
 	.version		= FIO_IOOPS_VERSION,
@@ -1200,6 +1228,10 @@ static struct ioengine_ops ioengine_uring_cmd = {
 	.open_file		= fio_ioring_cmd_open_file,
 	.close_file		= fio_ioring_cmd_close_file,
 	.get_file_size		= fio_ioring_cmd_get_file_size,
+	.get_zoned_model	= fio_ioring_cmd_get_zoned_model,
+	.report_zones		= fio_ioring_cmd_report_zones,
+	.reset_wp		= fio_ioring_cmd_reset_wp,
+	.get_max_open_zones	= fio_ioring_cmd_get_max_open_zones,
 	.options		= options,
 	.option_struct_size	= sizeof(struct ioring_options),
 };
diff --git a/engines/nvme.c b/engines/nvme.c
index 6fecf0ba..59550def 100644
--- a/engines/nvme.c
+++ b/engines/nvme.c
@@ -101,3 +101,245 @@ int fio_nvme_get_info(struct fio_file *f, __u32 *nsid, __u32 *lba_sz,
 	close(fd);
 	return 0;
 }
+
+int fio_nvme_get_zoned_model(struct thread_data *td, struct fio_file *f,
+			     enum zbd_zoned_model *model)
+{
+	struct nvme_data *data = FILE_ENG_DATA(f);
+	struct nvme_id_ns ns;
+	struct nvme_passthru_cmd cmd;
+	int fd, ret = 0;
+
+	if (f->filetype != FIO_TYPE_CHAR)
+		return -EINVAL;
+
+	/* File is not yet opened */
+	fd = open(f->file_name, O_RDONLY | O_LARGEFILE);
+	if (fd < 0)
+		return -errno;
+
+	/* Using nvme_id_ns for data as sizes are same */
+	ret = nvme_identify(fd, data->nsid, NVME_IDENTIFY_CNS_CSI_CTRL,
+				NVME_CSI_ZNS, &ns);
+	if (ret) {
+		*model = ZBD_NONE;
+		goto out;
+	}
+
+	memset(&cmd, 0, sizeof(struct nvme_passthru_cmd));
+
+	/* Using nvme_id_ns for data as sizes are same */
+	ret = nvme_identify(fd, data->nsid, NVME_IDENTIFY_CNS_CSI_NS,
+				NVME_CSI_ZNS, &ns);
+	if (ret) {
+		*model = ZBD_NONE;
+		goto out;
+	}
+
+	*model = ZBD_HOST_MANAGED;
+out:
+	close(fd);
+	return 0;
+}
+
+static int nvme_report_zones(int fd, __u32 nsid, __u64 slba, __u32 zras_feat,
+			     __u32 data_len, void *data)
+{
+	struct nvme_passthru_cmd cmd = {
+		.opcode         = nvme_zns_cmd_mgmt_recv,
+		.nsid           = nsid,
+		.addr           = (__u64)(uintptr_t)data,
+		.data_len       = data_len,
+		.cdw10          = slba & 0xffffffff,
+		.cdw11          = slba >> 32,
+		.cdw12		= (data_len >> 2) - 1,
+		.cdw13		= NVME_ZNS_ZRA_REPORT_ZONES | zras_feat,
+		.timeout_ms     = NVME_DEFAULT_IOCTL_TIMEOUT,
+	};
+
+	return ioctl(fd, NVME_IOCTL_IO_CMD, &cmd);
+}
+
+int fio_nvme_report_zones(struct thread_data *td, struct fio_file *f,
+			  uint64_t offset, struct zbd_zone *zbdz,
+			  unsigned int nr_zones)
+{
+	struct nvme_data *data = FILE_ENG_DATA(f);
+	struct nvme_zone_report *zr;
+	struct nvme_zns_id_ns zns_ns;
+	struct nvme_id_ns ns;
+	unsigned int i = 0, j, zones_fetched = 0;
+	unsigned int max_zones, zones_chunks = 1024;
+	int fd, ret = 0;
+	__u32 zr_len;
+	__u64 zlen;
+
+	/* File is not yet opened */
+	fd = open(f->file_name, O_RDONLY | O_LARGEFILE);
+	if (fd < 0)
+		return -errno;
+
+	zones_fetched = 0;
+	zr_len = sizeof(*zr) + (zones_chunks * sizeof(struct nvme_zns_desc));
+	zr = calloc(1, zr_len);
+	if (!zr)
+		return -ENOMEM;
+
+	ret = nvme_identify(fd, data->nsid, NVME_IDENTIFY_CNS_NS,
+				NVME_CSI_NVM, &ns);
+	if (ret) {
+		log_err("%s: nvme_identify_ns failed, err=%d\n", f->file_name,
+			ret);
+		goto out;
+	}
+
+	ret = nvme_identify(fd, data->nsid, NVME_IDENTIFY_CNS_CSI_NS,
+				NVME_CSI_ZNS, &zns_ns);
+	if (ret) {
+		log_err("%s: nvme_zns_identify_ns failed, err=%d\n",
+			f->file_name, ret);
+		goto out;
+	}
+	zlen = zns_ns.lbafe[ns.flbas & 0x0f].zsze << data->lba_shift;
+
+	max_zones = (f->real_file_size - offset) / zlen;
+	if (max_zones < nr_zones)
+		nr_zones = max_zones;
+
+	if (nr_zones < zones_chunks)
+		zones_chunks = nr_zones;
+
+	while (zones_fetched < nr_zones) {
+		if (zones_fetched + zones_chunks >= nr_zones) {
+			zones_chunks = nr_zones - zones_fetched;
+			zr_len = sizeof(*zr) + (zones_chunks * sizeof(struct nvme_zns_desc));
+		}
+		ret = nvme_report_zones(fd, data->nsid, offset >> data->lba_shift,
+					NVME_ZNS_ZRAS_FEAT_ERZ, zr_len, (void *)zr);
+		if (ret) {
+			log_err("%s: nvme_zns_report_zones failed, err=%d\n",
+				f->file_name, ret);
+			goto out;
+		}
+
+		/* Transform the zone-report */
+		for (j = 0; j < zr->nr_zones; j++, i++) {
+			struct nvme_zns_desc *desc = (struct nvme_zns_desc *)&(zr->entries[j]);
+
+			zbdz[i].start = desc->zslba << data->lba_shift;
+			zbdz[i].len = zlen;
+			zbdz[i].wp = desc->wp << data->lba_shift;
+			zbdz[i].capacity = desc->zcap << data->lba_shift;
+
+			/* Zone Type is stored in first 4 bits. */
+			switch (desc->zt & 0x0f) {
+			case NVME_ZONE_TYPE_SEQWRITE_REQ:
+				zbdz[i].type = ZBD_ZONE_TYPE_SWR;
+				break;
+			default:
+				log_err("%s: invalid type for zone at offset %llu.\n",
+					f->file_name, desc->zslba);
+				ret = -EIO;
+				goto out;
+			}
+
+			/* Zone State is stored in last 4 bits. */
+			switch (desc->zs >> 4) {
+			case NVME_ZNS_ZS_EMPTY:
+				zbdz[i].cond = ZBD_ZONE_COND_EMPTY;
+				break;
+			case NVME_ZNS_ZS_IMPL_OPEN:
+				zbdz[i].cond = ZBD_ZONE_COND_IMP_OPEN;
+				break;
+			case NVME_ZNS_ZS_EXPL_OPEN:
+				zbdz[i].cond = ZBD_ZONE_COND_EXP_OPEN;
+				break;
+			case NVME_ZNS_ZS_CLOSED:
+				zbdz[i].cond = ZBD_ZONE_COND_CLOSED;
+				break;
+			case NVME_ZNS_ZS_FULL:
+				zbdz[i].cond = ZBD_ZONE_COND_FULL;
+				break;
+			case NVME_ZNS_ZS_READ_ONLY:
+			case NVME_ZNS_ZS_OFFLINE:
+			default:
+				/* Treat all these conditions as offline (don't use!) */
+				zbdz[i].cond = ZBD_ZONE_COND_OFFLINE;
+				zbdz[i].wp = zbdz[i].start;
+			}
+		}
+		zones_fetched += zr->nr_zones;
+		offset += zr->nr_zones * zlen;
+	}
+
+	ret = zones_fetched;
+out:
+	free(zr);
+	close(fd);
+
+	return ret;
+}
+
+int fio_nvme_reset_wp(struct thread_data *td, struct fio_file *f,
+		      uint64_t offset, uint64_t length)
+{
+	struct nvme_data *data = FILE_ENG_DATA(f);
+	unsigned int nr_zones;
+	unsigned long long zslba;
+	int i, fd, ret = 0;
+
+	/* If the file is not yet opened, open it for this function. */
+	fd = f->fd;
+	if (fd < 0) {
+		fd = open(f->file_name, O_RDWR | O_LARGEFILE);
+		if (fd < 0)
+			return -errno;
+	}
+
+	zslba = offset >> data->lba_shift;
+	nr_zones = (length + td->o.zone_size - 1) / td->o.zone_size;
+
+	for (i = 0; i < nr_zones; i++, zslba += (td->o.zone_size >> data->lba_shift)) {
+		struct nvme_passthru_cmd cmd = {
+			.opcode         = nvme_zns_cmd_mgmt_send,
+			.nsid           = data->nsid,
+			.cdw10          = zslba & 0xffffffff,
+			.cdw11          = zslba >> 32,
+			.cdw13          = NVME_ZNS_ZSA_RESET,
+			.addr           = (__u64)(uintptr_t)NULL,
+			.data_len       = 0,
+			.timeout_ms     = NVME_DEFAULT_IOCTL_TIMEOUT,
+		};
+
+		ret = ioctl(fd, NVME_IOCTL_IO_CMD, &cmd);
+	}
+
+	if (f->fd < 0)
+		close(fd);
+	return -ret;
+}
+
+int fio_nvme_get_max_open_zones(struct thread_data *td, struct fio_file *f,
+				unsigned int *max_open_zones)
+{
+	struct nvme_data *data = FILE_ENG_DATA(f);
+	struct nvme_zns_id_ns zns_ns;
+	int fd, ret = 0;
+
+	fd = open(f->file_name, O_RDONLY | O_LARGEFILE);
+	if (fd < 0)
+		return -errno;
+
+	ret = nvme_identify(fd, data->nsid, NVME_IDENTIFY_CNS_CSI_NS,
+				NVME_CSI_ZNS, &zns_ns);
+	if (ret) {
+		log_err("%s: nvme_zns_identify_ns failed, err=%d\n",
+			f->file_name, ret);
+		goto out;
+	}
+
+	*max_open_zones = zns_ns.mor + 1;
+out:
+	close(fd);
+	return ret;
+}
diff --git a/engines/nvme.h b/engines/nvme.h
index 8e626bb2..70a89b74 100644
--- a/engines/nvme.h
+++ b/engines/nvme.h
@@ -43,8 +43,15 @@ struct nvme_uring_cmd {
 #define NVME_IDENTIFY_DATA_SIZE 4096
 #define NVME_IDENTIFY_CSI_SHIFT 24
 
+#define NVME_ZNS_ZRA_REPORT_ZONES 0
+#define NVME_ZNS_ZRAS_FEAT_ERZ (1 << 16)
+#define NVME_ZNS_ZSA_RESET 0x4
+#define NVME_ZONE_TYPE_SEQWRITE_REQ 0x2
+
 enum nvme_identify_cns {
-	NVME_IDENTIFY_CNS_NS = 0x00,
+	NVME_IDENTIFY_CNS_NS		= 0x00,
+	NVME_IDENTIFY_CNS_CSI_NS	= 0x05,
+	NVME_IDENTIFY_CNS_CSI_CTRL	= 0x06,
 };
 
 enum nvme_csi {
@@ -60,6 +67,18 @@ enum nvme_admin_opcode {
 enum nvme_io_opcode {
 	nvme_cmd_write			= 0x01,
 	nvme_cmd_read			= 0x02,
+	nvme_zns_cmd_mgmt_send		= 0x79,
+	nvme_zns_cmd_mgmt_recv		= 0x7a,
+};
+
+enum nvme_zns_zs {
+	NVME_ZNS_ZS_EMPTY		= 0x1,
+	NVME_ZNS_ZS_IMPL_OPEN		= 0x2,
+	NVME_ZNS_ZS_EXPL_OPEN		= 0x3,
+	NVME_ZNS_ZS_CLOSED		= 0x4,
+	NVME_ZNS_ZS_READ_ONLY		= 0xd,
+	NVME_ZNS_ZS_FULL		= 0xe,
+	NVME_ZNS_ZS_OFFLINE		= 0xf,
 };
 
 struct nvme_data {
@@ -127,10 +146,69 @@ static inline int ilog2(uint32_t i)
 	return log;
 }
 
+struct nvme_zns_lbafe {
+	__le64	zsze;
+	__u8	zdes;
+	__u8	rsvd9[7];
+};
+
+struct nvme_zns_id_ns {
+	__le16			zoc;
+	__le16			ozcs;
+	__le32			mar;
+	__le32			mor;
+	__le32			rrl;
+	__le32			frl;
+	__le32			rrl1;
+	__le32			rrl2;
+	__le32			rrl3;
+	__le32			frl1;
+	__le32			frl2;
+	__le32			frl3;
+	__le32			numzrwa;
+	__le16			zrwafg;
+	__le16			zrwasz;
+	__u8			zrwacap;
+	__u8			rsvd53[2763];
+	struct nvme_zns_lbafe	lbafe[64];
+	__u8			vs[256];
+};
+
+struct nvme_zns_desc {
+	__u8	zt;
+	__u8	zs;
+	__u8	za;
+	__u8	zai;
+	__u8	rsvd4[4];
+	__le64	zcap;
+	__le64	zslba;
+	__le64	wp;
+	__u8	rsvd32[32];
+};
+
+struct nvme_zone_report {
+	__le64			nr_zones;
+	__u8			rsvd8[56];
+	struct nvme_zns_desc	entries[];
+};
+
 int fio_nvme_get_info(struct fio_file *f, __u32 *nsid, __u32 *lba_sz,
 		      __u64 *nlba);
 
 int fio_nvme_uring_cmd_prep(struct nvme_uring_cmd *cmd, struct io_u *io_u,
 			    struct iovec *iov);
 
+int fio_nvme_get_zoned_model(struct thread_data *td, struct fio_file *f,
+			     enum zbd_zoned_model *model);
+
+int fio_nvme_report_zones(struct thread_data *td, struct fio_file *f,
+			  uint64_t offset, struct zbd_zone *zbdz,
+			  unsigned int nr_zones);
+
+int fio_nvme_reset_wp(struct thread_data *td, struct fio_file *f,
+		      uint64_t offset, uint64_t length);
+
+int fio_nvme_get_max_open_zones(struct thread_data *td, struct fio_file *f,
+				unsigned int *max_open_zones);
+
 #endif
-- 
2.17.1