[PATCH v10 10/12] hw/block/nvme: Support Zone Descriptor Extensions

[Dmitry Fomichev]

Zone Descriptor Extension is a label that can be assigned to a zone.
It can be set to an Empty zone and it stays assigned until the zone
is reset.

This commit adds a new optional module property,
"zoned.descr_ext_size". Its value must be a multiple of 64 bytes.
If this value is non-zero, it becomes possible to assign extensions
of that size to any Empty zones. The default value for this property
is 0, therefore setting extensions is disabled by default.

Signed-off-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com>
---
 hw/block/nvme-ns.h    |  8 +++++++
 hw/block/nvme-ns.c    | 25 ++++++++++++++++++--
 hw/block/nvme.c       | 54 +++++++++++++++++++++++++++++++++++++++++--
 hw/block/trace-events |  2 ++
 4 files changed, 85 insertions(+), 4 deletions(-)

diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
index 421bab0a57..50a6a0e1ac 100644
--- a/hw/block/nvme-ns.h
+++ b/hw/block/nvme-ns.h
@@ -35,6 +35,7 @@ typedef struct NvmeNamespaceParams {
     uint64_t zone_cap_bs;
     uint32_t max_active_zones;
     uint32_t max_open_zones;
+    uint32_t zd_extension_size;
 } NvmeNamespaceParams;
 
 typedef struct NvmeNamespace {
@@ -58,6 +59,7 @@ typedef struct NvmeNamespace {
     uint64_t        zone_capacity;
     uint64_t        zone_array_size;
     uint32_t        zone_size_log2;
+    uint8_t         *zd_extensions;
     int32_t         nr_open_zones;
     int32_t         nr_active_zones;
 
@@ -127,6 +129,12 @@ static inline bool nvme_wp_is_valid(NvmeZone *zone)
            st != NVME_ZONE_STATE_OFFLINE;
 }
 
+static inline uint8_t *nvme_get_zd_extension(NvmeNamespace *ns,
+                                             uint32_t zone_idx)
+{
+    return &ns->zd_extensions[zone_idx * ns->params.zd_extension_size];
+}
+
 static inline void nvme_aor_inc_open(NvmeNamespace *ns)
 {
     assert(ns->nr_open_zones >= 0);
diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index 2e45838c15..85dc73cf06 100644
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -133,6 +133,18 @@ static int nvme_calc_zone_geometry(NvmeNamespace *ns, 
Error **errp)
         return -1;
     }
 
+    if (ns->params.zd_extension_size) {
+        if (ns->params.zd_extension_size & 0x3f) {
+            error_setg(errp,
+                "zone descriptor extension size must be a multiple of 64B");
+            return -1;
+        }
+        if ((ns->params.zd_extension_size >> 6) > 0xff) {
+            error_setg(errp, "zone descriptor extension size is too large");
+            return -1;
+        }
+    }
+
     return 0;
 }
 
@@ -144,6 +156,10 @@ static void nvme_init_zone_state(NvmeNamespace *ns)
     int i;
 
     ns->zone_array = g_malloc0(ns->zone_array_size);
+    if (ns->params.zd_extension_size) {
+        ns->zd_extensions = g_malloc0(ns->params.zd_extension_size *
+                                      ns->num_zones);
+    }
 
     QTAILQ_INIT(&ns->exp_open_zones);
     QTAILQ_INIT(&ns->imp_open_zones);
@@ -186,7 +202,8 @@ static int nvme_zoned_init_ns(NvmeCtrl *n, NvmeNamespace 
*ns, int lba_index,
     id_ns_z->ozcs = ns->params.cross_zone_read ? 0x01 : 0x00;
 
     id_ns_z->lbafe[lba_index].zsze = cpu_to_le64(ns->zone_size);
-    id_ns_z->lbafe[lba_index].zdes = 0;
+    id_ns_z->lbafe[lba_index].zdes =
+        ns->params.zd_extension_size >> 6; /* Units of 64B */
 
     ns->csi = NVME_CSI_ZONED;
     ns->id_ns.nsze = cpu_to_le64(ns->zone_size * ns->num_zones);
@@ -204,7 +221,8 @@ static void nvme_clear_zone(NvmeNamespace *ns, NvmeZone 
*zone)
 
     zone->w_ptr = zone->d.wp;
     state = nvme_get_zone_state(zone);
-    if (zone->d.wp != zone->d.zslba) {
+    if (zone->d.wp != zone->d.zslba ||
+        (zone->d.za & NVME_ZA_ZD_EXT_VALID)) {
         if (state != NVME_ZONE_STATE_CLOSED) {
             trace_pci_nvme_clear_ns_close(state, zone->d.zslba);
             nvme_set_zone_state(zone, NVME_ZONE_STATE_CLOSED);
@@ -301,6 +319,7 @@ void nvme_ns_cleanup(NvmeNamespace *ns)
     if (ns->params.zoned) {
         g_free(ns->id_ns_zoned);
         g_free(ns->zone_array);
+        g_free(ns->zd_extensions);
     }
 }
 
@@ -332,6 +351,8 @@ static Property nvme_ns_props[] = {
                        params.max_active_zones, 0),
     DEFINE_PROP_UINT32("zoned.max_open", NvmeNamespace,
                        params.max_open_zones, 0),
+    DEFINE_PROP_UINT32("zoned.descr_ext_size", NvmeNamespace,
+                       params.zd_extension_size, 0),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index c6b3a5dcf7..e82e3be821 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -1703,6 +1703,26 @@ static uint16_t nvme_offline_zone(NvmeNamespace *ns, 
NvmeZone *zone,
     return NVME_ZONE_INVAL_TRANSITION;
 }
 
+static uint16_t nvme_set_zd_ext(NvmeNamespace *ns, NvmeZone *zone)
+{
+    uint16_t status;
+    uint8_t state = nvme_get_zone_state(zone);
+
+    if (state == NVME_ZONE_STATE_EMPTY) {
+        nvme_auto_transition_zone(ns, false, true);
+        status = nvme_aor_check(ns, 1, 0);
+        if (status != NVME_SUCCESS) {
+            return status;
+        }
+        nvme_aor_inc_active(ns);
+        zone->d.za |= NVME_ZA_ZD_EXT_VALID;
+        nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_CLOSED);
+        return NVME_SUCCESS;
+    }
+
+    return NVME_ZONE_INVAL_TRANSITION;
+}
+
 static uint16_t nvme_bulk_proc_zone(NvmeNamespace *ns, NvmeZone *zone,
                                     enum NvmeZoneProcessingMask proc_mask,
                                     op_handler_t op_hndlr)
@@ -1798,6 +1818,7 @@ static uint16_t nvme_zone_mgmt_send(NvmeCtrl *n, 
NvmeRequest *req)
     NvmeCmd *cmd = (NvmeCmd *)&req->cmd;
     NvmeNamespace *ns = req->ns;
     NvmeZone *zone;
+    uint8_t *zd_ext;
     uint32_t dw13 = le32_to_cpu(cmd->cdw13);
     uint64_t slba = 0;
     uint32_t zone_idx = 0;
@@ -1870,7 +1891,22 @@ static uint16_t nvme_zone_mgmt_send(NvmeCtrl *n, 
NvmeRequest *req)
 
     case NVME_ZONE_ACTION_SET_ZD_EXT:
         trace_pci_nvme_set_descriptor_extension(slba, zone_idx);
-        return NVME_INVALID_FIELD | NVME_DNR;
+        if (all || !ns->params.zd_extension_size) {
+            return NVME_INVALID_FIELD | NVME_DNR;
+        }
+        zd_ext = nvme_get_zd_extension(ns, zone_idx);
+        status = nvme_dma(n, zd_ext, ns->params.zd_extension_size,
+                          DMA_DIRECTION_TO_DEVICE, req);
+        if (status) {
+            trace_pci_nvme_err_zd_extension_map_error(zone_idx);
+            return status;
+        }
+
+        status = nvme_set_zd_ext(ns, zone);
+        if (status == NVME_SUCCESS) {
+            trace_pci_nvme_zd_extension_set(zone_idx);
+            return status;
+        }
         break;
 
     default:
@@ -1940,7 +1976,10 @@ static uint16_t nvme_zone_mgmt_recv(NvmeCtrl *n, 
NvmeRequest *req)
     }
 
     zra = dw13 & 0xff;
-    if (zra != NVME_ZONE_REPORT) {
+    if (zra != NVME_ZONE_REPORT && zra != NVME_ZONE_REPORT_EXTENDED) {
+        return NVME_INVALID_FIELD | NVME_DNR;
+    }
+    if (zra == NVME_ZONE_REPORT_EXTENDED && !ns->params.zd_extension_size) {
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
@@ -1962,6 +2001,9 @@ static uint16_t nvme_zone_mgmt_recv(NvmeCtrl *n, 
NvmeRequest *req)
     partial = (dw13 >> 16) & 0x01;
 
     zone_entry_sz = sizeof(NvmeZoneDescr);
+    if (zra == NVME_ZONE_REPORT_EXTENDED) {
+        zone_entry_sz += ns->params.zd_extension_size;
+    }
 
     max_zones = (data_size - sizeof(NvmeZoneReportHeader)) / zone_entry_sz;
     buf = g_malloc0(data_size);
@@ -1993,6 +2035,14 @@ static uint16_t nvme_zone_mgmt_recv(NvmeCtrl *n, 
NvmeRequest *req)
             z->wp = cpu_to_le64(~0ULL);
         }
 
+        if (zra == NVME_ZONE_REPORT_EXTENDED) {
+            if (zs->d.za & NVME_ZA_ZD_EXT_VALID) {
+                memcpy(buf_p, nvme_get_zd_extension(ns, zone_idx),
+                       ns->params.zd_extension_size);
+            }
+            buf_p += ns->params.zd_extension_size;
+        }
+
         zone_idx++;
     }
 
diff --git a/hw/block/trace-events b/hw/block/trace-events
index e674522883..d42d2c8d61 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -95,6 +95,7 @@ pci_nvme_finish_zone(uint64_t slba, uint32_t zone_idx, int 
all) "finish zone, sl
 pci_nvme_reset_zone(uint64_t slba, uint32_t zone_idx, int all) "reset zone, 
slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32""
 pci_nvme_offline_zone(uint64_t slba, uint32_t zone_idx, int all) "offline 
zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32""
 pci_nvme_set_descriptor_extension(uint64_t slba, uint32_t zone_idx) "set zone 
descriptor extension, slba=%"PRIu64", idx=%"PRIu32""
+pci_nvme_zd_extension_set(uint32_t zone_idx) "set descriptor extension for 
zone_idx=%"PRIu32""
 pci_nvme_clear_ns_close(uint32_t state, uint64_t slba) "zone state=%"PRIu32", 
slba=%"PRIu64" transitioned to Closed state"
 pci_nvme_clear_ns_reset(uint32_t state, uint64_t slba) "zone state=%"PRIu32", 
slba=%"PRIu64" transitioned to Empty state"
 
@@ -124,6 +125,7 @@ pci_nvme_err_zone_read_not_ok(uint64_t slba, uint32_t nlb, 
uint32_t status) "slb
 pci_nvme_err_append_too_large(uint64_t slba, uint32_t nlb, uint8_t zasl) 
"slba=%"PRIu64", nlb=%"PRIu32", zasl=%"PRIu8""
 pci_nvme_err_insuff_active_res(uint32_t max_active) "max_active=%"PRIu32" zone 
limit exceeded"
 pci_nvme_err_insuff_open_res(uint32_t max_open) "max_open=%"PRIu32" zone limit 
exceeded"
+pci_nvme_err_zd_extension_map_error(uint32_t zone_idx) "can't map descriptor 
extension for zone_idx=%"PRIu32""
 pci_nvme_err_invalid_iocsci(uint32_t idx) "unsupported command set combination 
index %"PRIu32""
 pci_nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, 
sid=%"PRIu16""
 pci_nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission 
queue, invalid cqid=%"PRIu16""
-- 
2.21.0