[PATCH v2 12/15] hw/block/nvme: Support Zone Descriptor Extensions

[Dmitry Fomichev <dmitry.fomichev@wdc.com>]

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, "zone_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>
---
 hw/block/nvme.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++---
 hw/block/nvme.h |  8 ++++++
 2 files changed, 77 insertions(+), 4 deletions(-)

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index df536fd736..ec7fade674 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -1355,6 +1355,26 @@ static bool nvme_cond_offline_all(uint8_t state)
     return state == NVME_ZONE_STATE_READ_ONLY;
 }
 
+static uint16_t nvme_set_zd_ext(NvmeCtrl *n, NvmeNamespace *ns,
+    NvmeZone *zone, uint8_t state)
+{
+    uint16_t status;
+
+    if (state == NVME_ZONE_STATE_EMPTY) {
+        nvme_auto_transition_zone(n, ns, false, true);
+        status = nvme_aor_check(n, ns, 1, 0);
+        if (status != NVME_SUCCESS) {
+            return status;
+        }
+        nvme_aor_inc_active(n, ns);
+        zone->d.za |= NVME_ZA_ZD_EXT_VALID;
+        nvme_assign_zone_state(n, ns, zone, NVME_ZONE_STATE_CLOSED);
+        return NVME_SUCCESS;
+    }
+
+    return NVME_ZONE_INVAL_TRANSITION;
+}
+
 typedef uint16_t (*op_handler_t)(NvmeCtrl *, NvmeNamespace *, NvmeZone *,
                                  uint8_t);
 typedef bool (*need_to_proc_zone_t)(uint8_t);
@@ -1389,12 +1409,14 @@ static uint16_t nvme_zone_mgmt_send(NvmeCtrl *n, NvmeRequest *req)
     NvmeCmd *cmd = (NvmeCmd *)&req->cmd;
     NvmeNamespace *ns = req->ns;
     uint32_t dw13 = le32_to_cpu(cmd->cdw13);
+    uint64_t prp1, prp2;
     uint64_t slba = 0;
     uint32_t zone_idx = 0;
     uint16_t status;
     uint8_t action, state;
     bool all;
     NvmeZone *zone;
+    uint8_t *zd_ext;
 
     action = dw13 & 0xff;
     all = dw13 & 0x100;
@@ -1449,7 +1471,24 @@ 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 || !n->params.zd_extension_size) {
+            return NVME_INVALID_FIELD | NVME_DNR;
+        }
+        zd_ext = nvme_get_zd_extension(n, ns, zone_idx);
+        prp1 = le64_to_cpu(cmd->dptr.prp1);
+        prp2 = le64_to_cpu(cmd->dptr.prp2);
+        status = nvme_dma_prp(n, zd_ext, n->params.zd_extension_size,
+                              prp1, prp2, DMA_DIRECTION_TO_DEVICE, req);
+        if (status) {
+            trace_pci_nvme_err_zd_extension_map_error(zone_idx);
+            return status;
+        }
+
+        status = nvme_set_zd_ext(n, ns, zone, state);
+        if (status == NVME_SUCCESS) {
+            trace_pci_nvme_zd_extension_set(zone_idx);
+            return status;
+        }
         break;
 
     default:
@@ -1529,7 +1568,7 @@ static uint16_t nvme_zone_mgmt_recv(NvmeCtrl *n, NvmeRequest *req)
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
-    if (zra == NVME_ZONE_REPORT_EXTENDED) {
+    if (zra == NVME_ZONE_REPORT_EXTENDED && !n->params.zd_extension_size) {
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
@@ -1541,6 +1580,9 @@ 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 += n->params.zd_extension_size;
+    }
 
     max_zones = (len - sizeof(NvmeZoneReportHeader)) / zone_entry_sz;
     buf = g_malloc0(len);
@@ -1572,6 +1614,14 @@ 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(n, ns, zone_idx),
+                       n->params.zd_extension_size);
+            }
+            buf_p += n->params.zd_extension_size;
+        }
+
         zone_idx++;
     }
 
@@ -2686,7 +2736,6 @@ static uint16_t nvme_aer(NvmeCtrl *n, NvmeRequest *req)
 
     n->aer_reqs[n->outstanding_aers] = req;
     n->outstanding_aers++;
-
     if (!QTAILQ_EMPTY(&n->aer_queue)) {
         nvme_process_aers(n);
     }
@@ -3320,6 +3369,7 @@ static int nvme_init_zone_meta(NvmeCtrl *n, NvmeNamespace *ns,
     ns->imp_open_zones = g_malloc0(sizeof(NvmeZoneList));
     ns->closed_zones = g_malloc0(sizeof(NvmeZoneList));
     ns->full_zones = g_malloc0(sizeof(NvmeZoneList));
+    ns->zd_extensions = g_malloc0(n->params.zd_extension_size * n->num_zones);
     zone = ns->zone_array;
 
     nvme_init_zone_list(ns->exp_open_zones);
@@ -3390,6 +3440,17 @@ static void nvme_zoned_init_ctrl(NvmeCtrl *n, Error **errp)
                     " adjusting", n->params.max_active_zones, nz);
         n->params.max_active_zones = nz;
     }
+    if (n->params.zd_extension_size) {
+        if (n->params.zd_extension_size & 0x3f) {
+            error_setg(errp,
+                "zone descriptor extension size must be a multiple of 64B");
+            return;
+        }
+        if ((n->params.zd_extension_size >> 6) > 0xff) {
+            error_setg(errp, "zone descriptor extension size is too large");
+            return;
+        }
+    }
 
     return;
 }
@@ -3414,7 +3475,8 @@ static int nvme_zoned_init_ns(NvmeCtrl *n, NvmeNamespace *ns, int lba_index,
     ns->id_ns_zoned->ozcs = n->params.cross_zone_read ? 0x01 : 0x00;
 
     ns->id_ns_zoned->lbafe[lba_index].zsze = cpu_to_le64(n->zone_size);
-    ns->id_ns_zoned->lbafe[lba_index].zdes = 0;
+    ns->id_ns_zoned->lbafe[lba_index].zdes =
+        n->params.zd_extension_size >> 6; /* Units of 64B */
 
     if (n->params.fill_pattern == 0) {
         ns->id_ns.dlfeat = 0x01;
@@ -3437,6 +3499,7 @@ static void nvme_zoned_clear(NvmeCtrl *n)
         g_free(ns->imp_open_zones);
         g_free(ns->closed_zones);
         g_free(ns->full_zones);
+        g_free(ns->zd_extensions);
     }
 }
 
@@ -3805,6 +3868,8 @@ static Property nvme_props[] = {
                        NVME_DEFAULT_ZONE_SIZE),
     DEFINE_PROP_UINT64("zone_capacity", NvmeCtrl, params.zone_capacity_mb, 0),
     DEFINE_PROP_UINT32("zone_append_size_limit", NvmeCtrl, params.zasl_kb, 0),
+    DEFINE_PROP_UINT32("zone_descr_ext_size", NvmeCtrl,
+                       params.zd_extension_size, 0),
     DEFINE_PROP_UINT32("max_active", NvmeCtrl, params.max_active_zones, 0),
     DEFINE_PROP_UINT32("max_open", NvmeCtrl, params.max_open_zones, 0),
     DEFINE_PROP_BOOL("cross_zone_read", NvmeCtrl, params.cross_zone_read, true),
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 4a3b23ed72..e53388ba66 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -24,6 +24,7 @@ typedef struct NvmeParams {
     uint64_t    zone_capacity_mb;
     uint32_t    max_active_zones;
     uint32_t    max_open_zones;
+    uint32_t    zd_extension_size;
 } NvmeParams;
 
 typedef struct NvmeAsyncEvent {
@@ -105,6 +106,7 @@ typedef struct NvmeNamespace {
     NvmeZoneList    *imp_open_zones;
     NvmeZoneList    *closed_zones;
     NvmeZoneList    *full_zones;
+    uint8_t         *zd_extensions;
     int32_t         nr_open_zones;
     int32_t         nr_active_zones;
 } NvmeNamespace;
@@ -218,6 +220,12 @@ static inline bool nvme_wp_is_valid(NvmeZone *zone)
            st != NVME_ZONE_STATE_OFFLINE;
 }
 
+static inline uint8_t *nvme_get_zd_extension(NvmeCtrl *n, NvmeNamespace *ns,
+                                             uint32_t zone_idx)
+{
+    return &ns->zd_extensions[zone_idx * n->params.zd_extension_size];
+}
+
 /*
  * Initialize a zone list head.
  */
-- 
2.21.0