Set and get DPM policy for GPU device

Add new APIs to set and get dpm policy for the GPU device.

Change-Id: I26fa49cd17d0ce66bda3446c38945a6cf35717ff

rocm_smi/src/rocm_smi.cc

@@ -145,6 +145,7 @@ static uint64_t get_multiplier_from_str(char units_char) {
   return multiplier;
 }
 
+
 /**
  * Parse a string of the form:
  *        "<int index>:  <int freq><freq. unit string> <|*>"
@@ -2014,6 +2015,133 @@ rsmi_dev_gpu_clk_freq_set(uint32_t dv_ind,
 
   CATCH
 }
+
+
+rsmi_status_t
+rsmi_dev_dpm_policy_set(uint32_t dv_ind,
+                      uint32_t policy_id) {
+  rsmi_status_t ret;
+
+  TRY
+  std::ostringstream ss;
+  ss << __PRETTY_FUNCTION__ << " | ======= start =======";
+  LOG_TRACE(ss);
+  REQUIRE_ROOT_ACCESS
+  DEVICE_MUTEX
+  GET_DEV_FROM_INDX
+
+  std::string value("soc_pstate ");
+  value += std::to_string(policy_id);
+  int ret = dev->writeDevInfo(amd::smi::kDevDPMPolicy , value);
+  return amd::smi::ErrnoToRsmiStatus(ret);
+
+  CATCH
+}
+
+rsmi_status_t
+rsmi_dev_dpm_policy_get(uint32_t dv_ind,
+                      rsmi_dpm_policy_t* policy) {
+  rsmi_status_t ret;
+  std::vector<std::string> val_vec;
+
+  if (policy == nullptr) {
+    return RSMI_STATUS_INVALID_ARGS;
+  }
+
+  *policy = {};
+
+  TRY
+  std::ostringstream ss;
+  ss << __PRETTY_FUNCTION__ << " | ======= start =======";
+  LOG_TRACE(ss);
+  DEVICE_MUTEX
+
+  ret = GetDevValueVec(amd::smi::kDevDPMPolicy, dv_ind, &val_vec);
+  if (ret == RSMI_STATUS_FILE_ERROR) {
+    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
+       << ", GetDevValueVec() ret was RSMI_STATUS_FILE_ERROR "
+       << "-> reporting RSMI_STATUS_NOT_SUPPORTED";
+    LOG_ERROR(ss);
+    return RSMI_STATUS_NOT_SUPPORTED;
+  }
+  if (ret != RSMI_STATUS_SUCCESS) {
+    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
+       << ", GetDevValueVec() ret was not RSMI_STATUS_SUCCESS"
+       << " -> reporting " << amd::smi::getRSMIStatusString(ret);
+    LOG_ERROR(ss);
+    return ret;
+  }
+  /*
+    It will reply on the number but no string as it may vary from soc to soc.
+    The current pstate marked with *
+    soc pstate
+    0 : soc_pstate_default
+    1 : soc_pstate_0
+    2 : soc_pstate_1*
+    3 : soc_pstate_2
+  */
+  bool see_soc_pstate = false;
+  bool see_current = false;
+  policy->num_supported = 0;
+  for (uint32_t i = 0; i < val_vec.size(); ++i) {
+    auto current_line = amd::smi::trim(val_vec[i]);
+    if (current_line == "soc pstate") {
+      see_soc_pstate = true;
+      continue;
+    }
+    if (see_soc_pstate == false) continue;
+
+    // Get tokens: <integer> : <string *>
+    std::vector<std::string> tokens;
+    std::istringstream f(current_line);
+    std::string s;
+    while (getline(f, s, ':')) {
+          tokens.push_back(s);
+    }
+
+    int value = 0;
+    // At the end
+    if (tokens.size() < 2 || !amd::smi::stringToInteger(tokens[0], value)) {
+      break;
+    }
+
+    if (value < 0 || policy->num_supported >= RSMI_MAX_NUM_PM_POLICIES) {
+      ss << __PRETTY_FUNCTION__ << " | ======= end ======="
+          << ", Unexpeced pstat data: the id is negative or too many policies.";
+          LOG_ERROR(ss);
+          return RSMI_STATUS_UNEXPECTED_DATA;
+    }
+
+    policy->policies[policy->num_supported].policy_id = value;
+    std::string description = amd::smi::trim(tokens[1]);
+    if (current_line.back() == '*') {  // current policy
+        description.pop_back();  // remove last *
+        description = amd::smi::trim(description);
+        policy->current = policy->num_supported;
+        see_current = true;
+    }
+    strncpy(policy->policies[policy->num_supported].policy_description,
+          description.c_str(),
+          RSMI_MAX_POLICY_NAME-1);
+    policy->num_supported++;
+  }  //  end for
+
+  if (!see_soc_pstate) {
+    return RSMI_STATUS_NOT_SUPPORTED;
+  }
+
+  if (!see_current) {
+      ss << __PRETTY_FUNCTION__ << " | ======= end ======="
+          << ", Unexpeced pstat data: cannot find the current policy.";
+          LOG_ERROR(ss);
+          return RSMI_STATUS_UNEXPECTED_DATA;
+  }
+  // Cannot find it
+  return RSMI_STATUS_SUCCESS;
+
+  CATCH
+}
+
 static std::vector<std::string> pci_name_files = {
   "/usr/share/misc/pci.ids",
   "/usr/share/hwdata/pci.ids",

rocm_smi/src/rocm_smi_device.cc

@@ -136,6 +136,7 @@ static const char *kDevAvailableComputePartitionFName =
                   "available_compute_partition";
 static const char *kDevComputePartitionFName = "current_compute_partition";
 static const char *kDevMemoryPartitionFName = "current_memory_partition";
+static const char* kDevDPMPolicyFName = "pm_policy";  // The PM policy for pstat and XGMI
 
 // Firmware version files
 static const char *kDevFwVersionAsdFName = "fw_version/asd_fw_version";
@@ -315,6 +316,7 @@ static const std::map<DevInfoTypes, const char *> kDevAttribNameMap = {
     {kDevNumaNode, kDevNumaNodeFName},
     {kDevGpuMetrics, kDevGpuMetricsFName},
     {kDevPmMetrics, kDevPmMetricsFName},
+    {kDevDPMPolicy, kDevDPMPolicyFName},
     {kDevRegMetrics, kDevRegMetricsFName},
     {kDevGpuReset, kDevGpuResetFName},
     {kDevAvailableComputePartition, kDevAvailableComputePartitionFName},
@@ -472,6 +474,7 @@ Device::devInfoTypesStrings = {
   {kDevComputePartition, "kDevComputePartition"},
   {kDevMemoryPartition, "kDevMemoryPartition"},
   {kDevPCieVendorID, "kDevPCieVendorID"},
+  {kDevDPMPolicy, "kDevDPMPolicy"},
 };
 
 static const std::map<const char *, dev_depends_t> kDevFuncDependsMap = {
@@ -533,6 +536,8 @@ static const std::map<const char *, dev_depends_t> kDevFuncDependsMap = {
   {"rsmi_topo_numa_affinity_get",        {{kDevNumaNodeFName}, {}}},
   {"rsmi_dev_gpu_metrics_info_get",      {{kDevGpuMetricsFName}, {}}},
   {"rsmi_dev_pm_metrics_info_get",       {{kDevPmMetricsFName}, {}}},
+  {"rsmi_dev_dpm_policy_get",           {{kDevDPMPolicyFName}, {}}},
+  {"rsmi_dev_dpm_policy_set",           {{kDevDPMPolicyFName}, {}}},
   {"rsmi_dev_reg_table_info_get",        {{kDevRegMetricsFName}, {}}},
   {"rsmi_dev_gpu_reset",                 {{kDevGpuResetFName}, {}}},
   {"rsmi_dev_compute_partition_get",     {{kDevComputePartitionFName}, {}}},
@@ -938,6 +943,7 @@ int Device::writeDevInfo(DevInfoTypes type, std::string val) {
     case kDevPCIEClk:
     case kDevPowerODVoltage:
     case kDevSOCClk:
+    case kDevDPMPolicy:
       return writeDevInfoStr(type, val);
     case kDevComputePartition:
     case kDevMemoryPartition:
@@ -1219,6 +1225,7 @@ int Device::readDevInfo(DevInfoTypes type, std::vector<std::string> *val) {
     case kDevErrCntHDP:
     case kDevErrCntXGMIWAFL:
     case kDevMemPageBad:
+    case kDevDPMPolicy:
       return readDevInfoMultiLineStr(type, val);
       break;
 

rocm_smi/src/rocm_smi_utils.cc

@@ -257,6 +257,16 @@ bool IsInteger(const std::string & n_str) {
   return (*tmp == 0);
 }
 
+bool stringToInteger(const std::string & n_str, int& value) {
+  try {
+    value = std::stoi(trim(n_str), nullptr);
+    return true;
+  } catch (...) {
+    return false;
+  }
+  return false;
+}
+
 rsmi_status_t handleException() {
   try {
     throw;