[SWDEV-423481/SWDEV-423393] Align all device identifier details

Updated: * [CLI] Fixed vram % - printf style formatting causes many data errors This fix updates to the recommended way of outputting formatted data. https://docs.python.org/3/library/stdtypes.html#printf-style-string-formatting * [API/CLI] Added gpu_id / GUID from kfd (rsmi_dev_guid_get) -> CLI name: "GUID" -> ROCm SMI calls: no arg, -i, --showhw, --showproduct * [API/CLI] Added node_id from kfd (rsmi_dev_node_get) -> CLI name: "Node" -> ROCm SMI calls: no arg, --showhw, --showproduct * [CLI] Added target gfx version from kfd -> CLI name: "GFX Version" or "GFX VER" -> ROCm SMI calls: --showhw, --showproduct * [CLI] Base ROCm CLI -> Removed - stacked id formatting: This is to simplify identifiers helpful to users. More identifiers can be found on -i --showhw, --showproduct * [CLI] Update -i, --showhw, --showproduct, w/out arg -> Card ID/DID/Model/SKU/VBIOS: All unsupported values now display "N/A" instead of "unknown" or "unsupported" * [CLI] Showhw now expands data based on content Change-Id: Ifb8586f9f545892b8a5aa7903608273cdd77e075 Signed-off-by: Charis Poag <Charis.Poag@amd.com> [ROCm/rocm_smi_lib commit: 4b5ccb57f0]
2024-01-31 21:03:33 -06:00
@@ -5143,11 +5143,12 @@ rsmi_status_t rsmi_dev_target_graphics_version_get(uint32_t dv_ind,
                                            uint64_t *gfx_version) {
    TRY
    std::ostringstream ss;
-    ss << __PRETTY_FUNCTION__ << "| ======= start =======";
+    ss << __PRETTY_FUNCTION__ << " | ======= start ======="
+       << " | Device #: " << dv_ind;
+    LOG_TRACE(ss);
    rsmi_status_t ret = RSMI_STATUS_NOT_SUPPORTED;
    std::string version = "";
    const uint64_t undefined_gfx_version = std::numeric_limits<uint64_t>::max();
-    LOG_TRACE(ss);
    if (gfx_version == nullptr) {
      ret = RSMI_STATUS_INVALID_ARGS;
    } else {
@@ -5160,15 +5161,80 @@ rsmi_status_t rsmi_dev_target_graphics_version_get(uint32_t dv_ind,
    }
    ss << __PRETTY_FUNCTION__
       << " | ======= end ======= "
-       << " | Returning: " << getRSMIStatusString(ret)
+       << " | Returning: " << getRSMIStatusString(ret, false)
       << " | Device #: " << dv_ind
-       << " | Type: N/A"
-       << " | Data: " << ((gfx_version == nullptr) ? "nullptr": std::to_string(*gfx_version));
+       << " | Type: Target_graphics_version"
+       << " | Data: "
+       << ((gfx_version == nullptr) ? "nullptr" :
+           amd::smi::print_unsigned_hex_and_int(*gfx_version));
    LOG_TRACE(ss);
    return ret;
    CATCH
 }

+rsmi_status_t rsmi_dev_guid_get(uint32_t dv_ind, uint64_t *guid) {
+    TRY
+    std::ostringstream ss;
+    ss << __PRETTY_FUNCTION__ << " | ======= start ======="
+       << " | Device #: " << dv_ind;
+    LOG_TRACE(ss);
+    GET_DEV_AND_KFDNODE_FROM_INDX
+    uint64_t kgd_gpu_id = 0;
+    rsmi_status_t resp = RSMI_STATUS_NOT_SUPPORTED;
+    int ret = kfd_node->KFDNode::get_gpu_id(&kgd_gpu_id);
+    resp = amd::smi::ErrnoToRsmiStatus(ret);
+
+    if (guid == nullptr) {
+      resp = RSMI_STATUS_INVALID_ARGS;
+    } else {
+      *guid = kgd_gpu_id;
+    }
+
+    ss << __PRETTY_FUNCTION__
+       << " | ======= end ======= "
+       << " | Returning: " << getRSMIStatusString(resp, false)
+       << " | Device #: " << dv_ind
+       << " | Type: GUID (gpu_id)"
+       << " | Data: " << ((guid == nullptr) ? "nullptr" :
+          amd::smi::print_unsigned_hex_and_int(*guid));
+    LOG_INFO(ss);
+    return resp;
+    CATCH
+}
+
+rsmi_status_t rsmi_dev_node_id_get(uint32_t dv_ind, uint32_t *node_id) {
+    TRY
+     std::ostringstream ss;
+    ss << __PRETTY_FUNCTION__ << " | ======= start ======="
+       << " | Device #: " << dv_ind;
+    LOG_TRACE(ss);
+    GET_DEV_AND_KFDNODE_FROM_INDX
+    uint32_t kgd_node_id = std::numeric_limits<uint32_t>::max();
+    rsmi_status_t resp = RSMI_STATUS_NOT_SUPPORTED;
+    int ret = kfd_node->KFDNode::get_node_id(&kgd_node_id);
+    resp = amd::smi::ErrnoToRsmiStatus(ret);
+
+    if (node_id == nullptr) {
+      resp = RSMI_STATUS_INVALID_ARGS;
+    } else {
+      *node_id = kgd_node_id;
+      if (kgd_node_id == std::numeric_limits<uint32_t>::max()) {
+        resp = RSMI_STATUS_NOT_SUPPORTED;
+      }
+    }
+
+    ss << __PRETTY_FUNCTION__
+       << " | ======= end ======= "
+       << " | Returning: " << getRSMIStatusString(resp, false)
+       << " | Device #: " << dv_ind
+       << " | Type: node_id"
+       << " | Data: " << ((node_id == nullptr) ? "nullptr" :
+          amd::smi::print_unsigned_hex_and_int(*node_id));
+    LOG_INFO(ss);
+    return resp;
+    CATCH
+}
+
 enum iterator_handle_type {
  FUNC_ITER = 0,
  VARIANT_ITER,
@@ -984,15 +984,72 @@ int KFDNode::get_gfx_target_version(uint64_t *gfx_target_version) {
  *gfx_target_version = gfx_version;
  ss << __PRETTY_FUNCTION__
     << " | File: " << properties_path
-     << " | Successfully read node #" << std::to_string(this->node_indx_)
+     << " | Read node: " << std::to_string(this->node_indx_)
     << " for gfx_target_version"
-     << " | Data (gfx_target_version) *gfx_target_version = "
+     << " | Data (*gfx_target_version): "
     << std::to_string(*gfx_target_version)
-     << " | return = " << std::to_string(ret)
+     << getRSMIStatusString(amd::smi::ErrnoToRsmiStatus(ret), false)
     << " | ";
  LOG_DEBUG(ss);
  return ret;
 }

+// Public interface for device
+// /sys/class/kfd/kfd/topology/nodes/*/gpu_id
+int KFDNode::get_gpu_id(uint64_t *gpu_id) {
+  std::ostringstream ss;
+  std::string gpuid_path = "/sys/class/kfd/kfd/topology/nodes/"
+    + std::to_string(this->node_indx_) + "/gpu_id";
+  const uint64_t undefined_gpu_id = std::numeric_limits<uint64_t>::max();
+  std::string gpu_id_string = "";
+  *gpu_id = undefined_gpu_id;
+  int ret = ReadSysfsStr(gpuid_path, &gpu_id_string);
+  if (ret != 0 || gpu_id_string.empty()) {
+    ss << __PRETTY_FUNCTION__
+       << " | File: " << gpuid_path
+       << " | Data (*gpu_id): empty or nullptr"
+       << " | Issue: Could not read node #" << std::to_string(this->node_indx_)
+       << ". KFD node was an unsupported node or value read was empty."
+       << " | Return: "
+       << getRSMIStatusString(amd::smi::ErrnoToRsmiStatus(ret), false)
+       << " | ";
+    LOG_ERROR(ss);
+    return ret;
+  }
+  *gpu_id = std::stoull(gpu_id_string);
+  if (*gpu_id == 0) {  // CPU node - return not supported
+    *gpu_id = undefined_gpu_id;
+    ret = ENOENT;  // map to RSMI_STATUS_NOT_SUPPORTED
+  }
+  ss << __PRETTY_FUNCTION__
+     << " | File: " << gpuid_path
+     << " | Read node #: " << std::to_string(this->node_indx_)
+     << " | Data (*gpu_id): " << std::to_string(*gpu_id)
+     << " | Return: "
+     << getRSMIStatusString(amd::smi::ErrnoToRsmiStatus(ret), false)
+     << " | ";
+  LOG_DEBUG(ss);
+  return ret;
+}
+
+// Public interface for device
+// /sys/class/kfd/kfd/topology/nodes/<node_id>
+int KFDNode::get_node_id(uint32_t *node_id) {
+  std::ostringstream ss;
+  int ret = 0;
+  std::string nodeid_path = "/sys/class/kfd/kfd/topology/nodes/"
+    + std::to_string(this->node_indx_);
+  ss << __PRETTY_FUNCTION__
+     << " | File: " << nodeid_path
+     << " | Read node #: " << std::to_string(this->node_indx_)
+     << " | Data (*node_id): " << std::to_string(*node_id)
+     << " | Return: "
+     << getRSMIStatusString(amd::smi::ErrnoToRsmiStatus(ret), false)
+     << " | ";
+  *node_id = this->node_indx_;
+  LOG_DEBUG(ss);
+  return ret;
+}
+
 }  // namespace smi
 }  // namespace amd