Flexible Data Placement (FDP), as ratified in TP 4146a, allows the host
to control the placement of logical blocks so as to reduce the SSD WAF.
Userspace can send the data lifetime information using the write hints.
The SCSI driver (sd) can already pass this information to the SCSI
devices. This patch does the same for NVMe.
Fetches the placement-identifiers (plids) if the device supports FDP.
And map the incoming write-hints to plids.
Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
Signed-off-by: Hui Qi <hui81.qi@xxxxxxxxxxx>
Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
---
drivers/nvme/host/core.c | 67 ++++++++++++++++++++++++++++++++++++++++
drivers/nvme/host/nvme.h | 4 +++
include/linux/nvme.h | 19 ++++++++++++
3 files changed, 90 insertions(+)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8ae0a2dc5eda..c3de06cff12f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -42,6 +42,20 @@ struct nvme_ns_info {
bool is_removed;
};
+struct nvme_fdp_ruh_status_desc {
+ u16 pid;
+ u16 ruhid;
+ u32 earutr;
+ u64 ruamw;
+ u8 rsvd16[16];
+};
+
+struct nvme_fdp_ruh_status {
+ u8 rsvd0[14];
+ u16 nruhsd;
+ struct nvme_fdp_ruh_status_desc ruhsd[];
+};
+
unsigned int admin_timeout = 60;
module_param(admin_timeout, uint, 0644);
MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands");
@@ -943,6 +957,16 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
return BLK_STS_OK;
}
+static inline void nvme_assign_placement_id(struct nvme_ns *ns,
+ struct request *req,
+ struct nvme_command *cmd)
+{
+ enum rw_hint h = min(ns->head->nr_plids, req->write_hint);
+
+ cmd->rw.control |= cpu_to_le16(NVME_RW_DTYPE_DPLCMT);
+ cmd->rw.dsmgmt |= cpu_to_le32(ns->head->plids[h] << 16);
+}
+
static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd,
enum nvme_opcode op)
@@ -1058,6 +1082,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
break;
case REQ_OP_WRITE:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
+ if (!ret && ns->head->nr_plids)
+ nvme_assign_placement_id(ns, req, cmd);
break;
case REQ_OP_ZONE_APPEND:
ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
@@ -2070,6 +2096,40 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
return ret;
}
+static int nvme_fetch_fdp_plids(struct nvme_ns *ns, u32 nsid)
+{
+ struct nvme_command c = {};
+ struct nvme_fdp_ruh_status *ruhs;
+ struct nvme_fdp_ruh_status_desc *ruhsd;
+ int size, ret, i;
+
+ size = sizeof(*ruhs) + NVME_MAX_PLIDS * sizeof(*ruhsd);
+ ruhs = kzalloc(size, GFP_KERNEL);
+ if (!ruhs)
+ return -ENOMEM;
+
+ c.imr.opcode = nvme_cmd_io_mgmt_recv;
+ c.imr.nsid = cpu_to_le32(nsid);
+ c.imr.mo = 0x1;
+ c.imr.numd = cpu_to_le32((size >> 2) - 1);
+
+ ret = nvme_submit_sync_cmd(ns->queue, &c, ruhs, size);
+ if (ret)
+ goto out;
+
+ ns->head->nr_plids = le16_to_cpu(ruhs->nruhsd);
+ ns->head->nr_plids =
+ min_t(u16, ns->head->nr_plids, NVME_MAX_PLIDS);
+
+ for (i = 0; i < ns->head->nr_plids; i++) {
+ ruhsd = &ruhs->ruhsd[i];
+ ns->head->plids[i] = le16_to_cpu(ruhsd->pid);
+ }
+out:
+ kfree(ruhs);
+ return ret;
+}
+
static int nvme_update_ns_info_block(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
@@ -2157,6 +2217,13 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if (ret && !nvme_first_scan(ns->disk))
goto out;
}
+ if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) {
+ ret = nvme_fetch_fdp_plids(ns, info->nsid);
+ if (ret)
+ dev_warn(ns->ctrl->device,
+ "FDP failure status:0x%x\n", ret);
+ }
+
ret = 0;
out:
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index d0ed64dc7380..67dad29fe289 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -440,6 +440,8 @@ struct nvme_ns_ids {
u8 csi;
};
+#define NVME_MAX_PLIDS (128)
+
/*
* Anchor structure for namespaces. There is one for each namespace in a
* NVMe subsystem that any of our controllers can see, and the namespace
@@ -457,6 +459,8 @@ struct nvme_ns_head {
bool shared;
bool passthru_err_log_enabled;
int instance;
+ u16 nr_plids;
+ u16 plids[NVME_MAX_PLIDS];
struct nvme_effects_log *effects;
u64 nuse;
unsigned ns_id;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 425573202295..fc07ba1b5ec5 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -270,6 +270,7 @@ enum nvme_ctrl_attr {
NVME_CTRL_ATTR_HID_128_BIT = (1 << 0),
NVME_CTRL_ATTR_TBKAS = (1 << 6),
NVME_CTRL_ATTR_ELBAS = (1 << 15),
+ NVME_CTRL_ATTR_FDPS = (1 << 19),
};
struct nvme_id_ctrl {
@@ -829,6 +830,7 @@ enum nvme_opcode {
nvme_cmd_resv_register = 0x0d,
nvme_cmd_resv_report = 0x0e,
nvme_cmd_resv_acquire = 0x11,
+ nvme_cmd_io_mgmt_recv = 0x12,
nvme_cmd_resv_release = 0x15,
nvme_cmd_zone_mgmt_send = 0x79,
nvme_cmd_zone_mgmt_recv = 0x7a,
@@ -850,6 +852,7 @@ enum nvme_opcode {
nvme_opcode_name(nvme_cmd_resv_register), \
nvme_opcode_name(nvme_cmd_resv_report), \
nvme_opcode_name(nvme_cmd_resv_acquire), \
+ nvme_opcode_name(nvme_cmd_io_mgmt_recv), \
nvme_opcode_name(nvme_cmd_resv_release), \
nvme_opcode_name(nvme_cmd_zone_mgmt_send), \
nvme_opcode_name(nvme_cmd_zone_mgmt_recv), \
@@ -1001,6 +1004,7 @@ enum {
NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12,
NVME_RW_PRINFO_PRACT = 1 << 13,
NVME_RW_DTYPE_STREAMS = 1 << 4,
+ NVME_RW_DTYPE_DPLCMT = 2 << 4,
NVME_WZ_DEAC = 1 << 9,
};
@@ -1088,6 +1092,20 @@ struct nvme_zone_mgmt_recv_cmd {
__le32 cdw14[2];
};
+struct nvme_io_mgmt_recv_cmd {
+ __u8 opcode;
+ __u8 flags;
+ __u16 command_id;
+ __le32 nsid;
+ __le64 rsvd2[2];
+ union nvme_data_ptr dptr;
+ __u8 mo;
+ __u8 rsvd11;
+ __u16 mos;
+ __le32 numd;
+ __le32 cdw12[4];
+};
+
enum {
NVME_ZRA_ZONE_REPORT = 0,
NVME_ZRASF_ZONE_REPORT_ALL = 0,
@@ -1808,6 +1826,7 @@ struct nvme_command {
struct nvmf_auth_receive_command auth_receive;
struct nvme_dbbuf dbbuf;
struct nvme_directive_cmd directive;
+ struct nvme_io_mgmt_recv_cmd imr;
};
};
--
2.25.1
